Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2936. Min Range: -6.2936
Max Act: 6.2936. Min Act: -0.1700
Data Index: 2425299 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.9186. Min Act: -0.1700
Data Index: 2219043 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.7623. Min Act: -0.1700
Data Index: 5802172 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.7311. Min Act: -0.1700
Data Index: 563035 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.6061. Min Act: -0.1700
Data Index: 7345990 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.6061. Min Act: -0.1700
Data Index: 6893433 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.5748. Min Act: -0.1700
Data Index: 771063 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.5123. Min Act: -0.1700
Data Index: 8564981 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.5123. Min Act: -0.1700
Data Index: 3338684 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.5123. Min Act: -0.1700
Data Index: 1575779 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.5436. Min Act: -0.1700
Data Index: 4376369 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.5436. Min Act: -0.1700
Data Index: 7389508 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.5123. Min Act: -0.1700
Data Index: 6860666 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4811. Min Act: -0.1700
Data Index: 2957752 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4811. Min Act: -0.1700
Data Index: 2885175 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4498. Min Act: -0.1700
Data Index: 7199098 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4498. Min Act: -0.1700
Data Index: 5393281 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4498. Min Act: -0.1700
Data Index: 232234 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4186. Min Act: -0.1700
Data Index: 2962903 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2936. Min Range: -6.2936
Max Act: 5.4186. Min Act: -0.1700
Data Index: 361056 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19