Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.4608. Min Act: -0.1700
Data Index: 4658583 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.2421. Min Act: -0.1700
Data Index: 8324109 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.1796. Min Act: -0.1700
Data Index: 8626831 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.0858. Min Act: -0.1700
Data Index: 3782459 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.0233. Min Act: -0.1700
Data Index: 4199747 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.0233. Min Act: -0.1700
Data Index: 754279 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.0233. Min Act: -0.1700
Data Index: 126800 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.0233. Min Act: -0.1700
Data Index: 4644707 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.0233. Min Act: -0.1700
Data Index: 4563630 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4608. Min Range: -6.4608
Max Act: 6.0233. Min Act: -0.1700
Data Index: 3459696 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.9921. Min Act: -0.1700
Data Index: 8675328 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.9921. Min Act: -0.1700
Data Index: 4434592 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.9608. Min Act: -0.1700
Data Index: 3223994 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.9921. Min Act: -0.1700
Data Index: 5101841 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.9296. Min Act: -0.1700
Data Index: 7368468 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.9296. Min Act: -0.1700
Data Index: 797740 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.8983. Min Act: -0.1700
Data Index: 8138396 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.9296. Min Act: -0.1700
Data Index: 1961868 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.9296. Min Act: -0.1700
Data Index: 969902 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4608. Min Range: -6.4608
Max Act: 5.9296. Min Act: -0.1700
Data Index: 1529389 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19