Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 75 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.6173. Min Act: -0.1700
Data Index: 2770608 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.5233. Min Act: -0.1700
Data Index: 1864584 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.3980. Min Act: -0.1700
Data Index: 1037629 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.3980. Min Act: -0.1700
Data Index: 8190831 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.3196. Min Act: -0.1700
Data Index: 3576029 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2725. Min Act: -0.1700
Data Index: 5273116 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2725. Min Act: -0.1700
Data Index: 6958147 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2725. Min Act: -0.1700
Data Index: 5385347 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2568. Min Act: -0.1700
Data Index: 5434517 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2410. Min Act: -0.1700
Data Index: 5941057 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2410. Min Act: -0.1700
Data Index: 8799602 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2253. Min Act: -0.1700
Data Index: 8413388 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2568. Min Act: -0.1700
Data Index: 3326486 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2096. Min Act: -0.1700
Data Index: 3717290 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.1939. Min Act: -0.1700
Data Index: 380216 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2096. Min Act: -0.1700
Data Index: 4532848 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.1939. Min Act: -0.1700
Data Index: 3711410 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.1939. Min Act: -0.1700
Data Index: 3112385 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.2096. Min Act: -0.1700
Data Index: 2949731 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6173. Min Range: -3.6173
Max Act: 3.1939. Min Act: -0.1700
Data Index: 5038365 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19