Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.4634. Min Act: -0.1700
Data Index: 7792066 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.4634. Min Act: -0.1700
Data Index: 383875 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.3072. Min Act: -0.1700
Data Index: 2855113 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.2447. Min Act: -0.1700
Data Index: 6128821 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.1822. Min Act: -0.1700
Data Index: 5940366 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.2134. Min Act: -0.1700
Data Index: 6970522 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.2134. Min Act: -0.1700
Data Index: 6899829 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.1822. Min Act: -0.1700
Data Index: 4296583 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.1822. Min Act: -0.1700
Data Index: 383878 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.1509. Min Act: -0.1700
Data Index: 4508897 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.1509. Min Act: -0.1700
Data Index: 1121229 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.1509. Min Act: -0.1700
Data Index: 7261789 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.1197. Min Act: -0.1700
Data Index: 6402323 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.1197. Min Act: -0.1700
Data Index: 3066748 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.0884. Min Act: -0.1700
Data Index: 1019325 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.0572. Min Act: -0.1700
Data Index: 8068115 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.0572. Min Act: -0.1700
Data Index: 1247678 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.0572. Min Act: -0.1700
Data Index: 5404528 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.0572. Min Act: -0.1700
Data Index: 4510357 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4634. Min Range: -5.4634
Max Act: 5.0259. Min Act: -0.1700
Data Index: 710818 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19