Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3974 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3866. Min Range: -7.3866
Max Act: 7.3866. Min Act: -0.1700
Data Index: 3727828 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.5428. Min Act: -0.1700
Data Index: 3942081 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.3866. Min Act: -0.1700
Data Index: 319046 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.3866. Min Act: -0.1700
Data Index: 1756607 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.3553. Min Act: -0.1700
Data Index: 829127 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.3241. Min Act: -0.1700
Data Index: 924715 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.2928. Min Act: -0.1700
Data Index: 7282421 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.2303. Min Act: -0.1700
Data Index: 7914534 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1991. Min Act: -0.1700
Data Index: 1810291 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1366. Min Act: -0.1700
Data Index: 7312937 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1678. Min Act: -0.1700
Data Index: 3371947 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1678. Min Act: -0.1700
Data Index: 3060597 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1366. Min Act: -0.1700
Data Index: 1532498 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1366. Min Act: -0.1700
Data Index: 76728 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1366. Min Act: -0.1700
Data Index: 7919373 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1366. Min Act: -0.1700
Data Index: 8418556 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1366. Min Act: -0.1700
Data Index: 5588145 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1053. Min Act: -0.1700
Data Index: 8138903 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1053. Min Act: -0.1700
Data Index: 6020127 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3866. Min Range: -7.3866
Max Act: 6.1366. Min Act: -0.1700
Data Index: 4409829 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19