Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.6489. Min Act: -0.1700
Data Index: 3158827 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.5552. Min Act: -0.1700
Data Index: 1823956 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4927. Min Act: -0.1700
Data Index: 3857524 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4927. Min Act: -0.1700
Data Index: 95938 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4614. Min Act: -0.1700
Data Index: 577217 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4302. Min Act: -0.1700
Data Index: 3771339 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4302. Min Act: -0.1700
Data Index: 6852794 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3989. Min Act: -0.1700
Data Index: 988654 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4302. Min Act: -0.1700
Data Index: 3191949 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3989. Min Act: -0.1700
Data Index: 5782187 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3677. Min Act: -0.1700
Data Index: 2611410 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3677. Min Act: -0.1700
Data Index: 1992491 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3677. Min Act: -0.1700
Data Index: 2787841 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3364. Min Act: -0.1700
Data Index: 7733435 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3052. Min Act: -0.1700
Data Index: 7426697 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3052. Min Act: -0.1700
Data Index: 6205482 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.2739. Min Act: -0.1700
Data Index: 7257532 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.2739. Min Act: -0.1700
Data Index: 988655 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3052. Min Act: -0.1700
Data Index: 6386685 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.2739. Min Act: -0.1700
Data Index: 4078382 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19