Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4975 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.1939. Min Act: -0.1700
Data Index: 7194157 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.1314. Min Act: -0.1700
Data Index: 3225398 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.1001. Min Act: -0.1700
Data Index: 2205244 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.0376. Min Act: -0.1700
Data Index: 1403309 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.0376. Min Act: -0.1700
Data Index: 8145779 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9751. Min Act: -0.1700
Data Index: 2969719 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1939. Min Range: -6.1939
Max Act: 6.0064. Min Act: -0.1700
Data Index: 3435274 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9751. Min Act: -0.1700
Data Index: 916724 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9751. Min Act: -0.1700
Data Index: 4957794 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9751. Min Act: -0.1700
Data Index: 8371832 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9439. Min Act: -0.1700
Data Index: 1751758 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9439. Min Act: -0.1700
Data Index: 3659329 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9126. Min Act: -0.1700
Data Index: 1609986 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9439. Min Act: -0.1700
Data Index: 7267766 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9126. Min Act: -0.1700
Data Index: 7458315 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9126. Min Act: -0.1700
Data Index: 5524653 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9126. Min Act: -0.1700
Data Index: 171110 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.9126. Min Act: -0.1700
Data Index: 4988228 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.8814. Min Act: -0.1700
Data Index: 112727 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1939. Min Range: -6.1939
Max Act: 5.8814. Min Act: -0.1700
Data Index: 6533453 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19