Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0135. Min Range: -6.0135
Max Act: 6.0135. Min Act: -0.1700
Data Index: 2174009 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.9823. Min Act: -0.1700
Data Index: 423097 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.9823. Min Act: -0.1700
Data Index: 4387290 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.9510. Min Act: -0.1700
Data Index: 3626651 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.9510. Min Act: -0.1700
Data Index: 8349572 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.9510. Min Act: -0.1700
Data Index: 959875 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.9198. Min Act: -0.1700
Data Index: 1061408 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8885. Min Act: -0.1700
Data Index: 3095269 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8885. Min Act: -0.1700
Data Index: 4593225 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8885. Min Act: -0.1700
Data Index: 8313045 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8885. Min Act: -0.1700
Data Index: 4454921 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8885. Min Act: -0.1700
Data Index: 4181423 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8885. Min Act: -0.1700
Data Index: 1731086 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8885. Min Act: -0.1700
Data Index: 7571129 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8885. Min Act: -0.1700
Data Index: 5777100 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8573. Min Act: -0.1700
Data Index: 4917114 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8573. Min Act: -0.1700
Data Index: 959878 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8573. Min Act: -0.1700
Data Index: 959873 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8573. Min Act: -0.1700
Data Index: 5370933 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0135. Min Range: -6.0135
Max Act: 5.8573. Min Act: -0.1700
Data Index: 351572 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19