Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 546 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.7834. Min Act: -0.1700
Data Index: 2296350 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5912. Min Act: -0.1700
Data Index: 7048032 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5912. Min Act: -0.1700
Data Index: 7816484 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5429. Min Act: -0.1700
Data Index: 4484683 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5590. Min Act: -0.1700
Data Index: 2126950 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5429. Min Act: -0.1700
Data Index: 6152521 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5590. Min Act: -0.1700
Data Index: 817537 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5267. Min Act: -0.1700
Data Index: 6663892 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5267. Min Act: -0.1700
Data Index: 725933 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5267. Min Act: -0.1700
Data Index: 1371030 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5105. Min Act: -0.1700
Data Index: 4353607 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5105. Min Act: -0.1700
Data Index: 1036499 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5105. Min Act: -0.1700
Data Index: 6308817 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5105. Min Act: -0.1700
Data Index: 5942585 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5105. Min Act: -0.1700
Data Index: 5847955 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.4943. Min Act: -0.1700
Data Index: 5675352 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.5105. Min Act: -0.1700
Data Index: 810972 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.4943. Min Act: -0.1700
Data Index: 5395330 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.4943. Min Act: -0.1700
Data Index: 5130565 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7834. Min Range: -2.7834
Max Act: 2.4943. Min Act: -0.1700
Data Index: 3312746 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19