Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5774 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4177. Min Range: -6.4177
Max Act: 6.4177. Min Act: -0.1700
Data Index: 2946633 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4177. Min Range: -6.4177
Max Act: 6.4177. Min Act: -0.1700
Data Index: 1806012 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4177. Min Range: -6.4177
Max Act: 6.3552. Min Act: -0.1700
Data Index: 3177883 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4177. Min Range: -6.4177
Max Act: 6.1989. Min Act: -0.1700
Data Index: 1812506 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4177. Min Range: -6.4177
Max Act: 6.0427. Min Act: -0.1700
Data Index: 7038154 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4177. Min Range: -6.4177
Max Act: 6.0114. Min Act: -0.1700
Data Index: 6143430 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4177. Min Range: -6.4177
Max Act: 6.0427. Min Act: -0.1700
Data Index: 7585926 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4177. Min Range: -6.4177
Max Act: 6.0114. Min Act: -0.1700
Data Index: 5033817 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.9802. Min Act: -0.1700
Data Index: 2342934 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4177. Min Range: -6.4177
Max Act: 6.0114. Min Act: -0.1700
Data Index: 422349 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.9802. Min Act: -0.1700
Data Index: 4993709 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.9489. Min Act: -0.1700
Data Index: 484630 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.9489. Min Act: -0.1700
Data Index: 3019074 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.9177. Min Act: -0.1700
Data Index: 8505025 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.9177. Min Act: -0.1700
Data Index: 5127659 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.9177. Min Act: -0.1700
Data Index: 2061655 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.9177. Min Act: -0.1700
Data Index: 3715654 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.8864. Min Act: -0.1700
Data Index: 3525613 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.8864. Min Act: -0.1700
Data Index: 6482937 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4177. Min Range: -6.4177
Max Act: 5.8864. Min Act: -0.1700
Data Index: 313252 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19