Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1397 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5880. Min Range: -6.5880
Max Act: 6.5880. Min Act: -0.1700
Data Index: 3133096 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.9630. Min Act: -0.1700
Data Index: 4831512 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.9005. Min Act: -0.1700
Data Index: 1466239 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.8380. Min Act: -0.1700
Data Index: 618868 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.8380. Min Act: -0.1700
Data Index: 2147800 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.8068. Min Act: -0.1700
Data Index: 4153303 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.7755. Min Act: -0.1700
Data Index: 3043090 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.7755. Min Act: -0.1700
Data Index: 5371071 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.7443. Min Act: -0.1700
Data Index: 4529206 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.7130. Min Act: -0.1700
Data Index: 2576417 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.6818. Min Act: -0.1700
Data Index: 8378228 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.6193. Min Act: -0.1700
Data Index: 2045480 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.6193. Min Act: -0.1700
Data Index: 3517731 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.6193. Min Act: -0.1700
Data Index: 4825863 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.5880. Min Act: -0.1700
Data Index: 289486 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.5880. Min Act: -0.1700
Data Index: 8805363 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.5880. Min Act: -0.1700
Data Index: 4036337 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.5568. Min Act: -0.1700
Data Index: 7788630 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.4943. Min Act: -0.1700
Data Index: 723926 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5880. Min Range: -6.5880
Max Act: 5.5255. Min Act: -0.1700
Data Index: 5792073 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19