Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 842 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2185. Min Range: -6.2185
Max Act: 6.2185. Min Act: -0.1700
Data Index: 37188 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2185. Min Range: -6.2185
Max Act: 6.2185. Min Act: -0.1700
Data Index: 5793103 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9685. Min Act: -0.1700
Data Index: 3576812 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9060. Min Act: -0.1700
Data Index: 7745084 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.9060. Min Act: -0.1700
Data Index: 7694294 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.8747. Min Act: -0.1700
Data Index: 2393 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.8747. Min Act: -0.1700
Data Index: 3713899 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.8435. Min Act: -0.1700
Data Index: 5577070 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.7810. Min Act: -0.1700
Data Index: 6614329 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.7810. Min Act: -0.1700
Data Index: 8192030 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.7810. Min Act: -0.1700
Data Index: 7533731 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.7810. Min Act: -0.1700
Data Index: 7757377 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.7497. Min Act: -0.1700
Data Index: 1594130 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.7497. Min Act: -0.1700
Data Index: 4057523 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.7185. Min Act: -0.1700
Data Index: 7946584 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.7185. Min Act: -0.1700
Data Index: 8419397 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.6560. Min Act: -0.1700
Data Index: 1084616 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.6872. Min Act: -0.1700
Data Index: 5221851 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.6872. Min Act: -0.1700
Data Index: 4982322 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2185. Min Range: -6.2185
Max Act: 5.6872. Min Act: -0.1700
Data Index: 4474751 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19