Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4409 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2091. Min Range: -12.2091
Max Act: 12.2091. Min Act: -0.1700
Data Index: 5451953 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2091. Min Range: -12.2091
Max Act: 12.1466. Min Act: -0.1700
Data Index: 8291013 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.9591. Min Act: -0.1700
Data Index: 4593113 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.9591. Min Act: -0.1700
Data Index: 3967021 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.8966. Min Act: -0.1700
Data Index: 6254387 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.8341. Min Act: -0.1700
Data Index: 7279384 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.8341. Min Act: -0.1700
Data Index: 4670863 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.7716. Min Act: -0.1700
Data Index: 6254374 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.8341. Min Act: -0.1700
Data Index: 2413836 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.7091. Min Act: -0.1700
Data Index: 3316317 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.7091. Min Act: -0.1700
Data Index: 7934248 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.6466. Min Act: -0.1700
Data Index: 6272543 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.5841. Min Act: -0.1700
Data Index: 3597365 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.5841. Min Act: -0.1700
Data Index: 6137156 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.5216. Min Act: -0.1700
Data Index: 2725109 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.5216. Min Act: -0.1700
Data Index: 4607829 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.5216. Min Act: -0.1700
Data Index: 8309442 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.5216. Min Act: -0.1700
Data Index: 5775228 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.5216. Min Act: -0.1700
Data Index: 519639 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2091. Min Range: -12.2091
Max Act: 11.4591. Min Act: -0.1700
Data Index: 5037486 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19