Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5230 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.3701. Min Act: -0.1700
Data Index: 6450700 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.3858. Min Act: -0.1700
Data Index: 3438280 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.3701. Min Act: -0.1700
Data Index: 5694608 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.2916. Min Act: -0.1700
Data Index: 4597730 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.3073. Min Act: -0.1700
Data Index: 1769142 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.2916. Min Act: -0.1700
Data Index: 6141425 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.2131. Min Act: -0.1700
Data Index: 4646106 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1974. Min Act: -0.1700
Data Index: 5040256 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1974. Min Act: -0.1700
Data Index: 3203522 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1816. Min Act: -0.1700
Data Index: 3438278 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1816. Min Act: -0.1700
Data Index: 7301434 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1659. Min Act: -0.1700
Data Index: 255142 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1502. Min Act: -0.1700
Data Index: 1269363 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1344. Min Act: -0.1700
Data Index: 4917074 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1502. Min Act: -0.1700
Data Index: 460320 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1344. Min Act: -0.1700
Data Index: 7532756 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1187. Min Act: -0.1700
Data Index: 7516575 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1029. Min Act: -0.1700
Data Index: 7471957 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1187. Min Act: -0.1700
Data Index: 460334 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3858. Min Range: -3.3858
Max Act: 3.1187. Min Act: -0.1700
Data Index: 980656 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19