Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1461 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.8450. Min Act: -0.1700
Data Index: 1968415 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.5950. Min Act: -0.1700
Data Index: 3243909 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.5950. Min Act: -0.1700
Data Index: 6186034 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4700. Min Act: -0.1700
Data Index: 1586049 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 7510630 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 8156010 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 2547636 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 2135352 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 4834064 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 1062932 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4075. Min Act: -0.1700
Data Index: 3854626 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.3762. Min Act: -0.1700
Data Index: 8317353 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.3450. Min Act: -0.1700
Data Index: 2114598 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.3450. Min Act: -0.1700
Data Index: 3443714 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.3137. Min Act: -0.1700
Data Index: 8283129 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.3137. Min Act: -0.1700
Data Index: 3038080 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.2825. Min Act: -0.1700
Data Index: 6561858 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.2825. Min Act: -0.1700
Data Index: 4587865 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.2825. Min Act: -0.1700
Data Index: 682280 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.2512. Min Act: -0.1700
Data Index: 3510864 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19