Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.5864. Min Act: -0.1700
Data Index: 7795050 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.5864. Min Act: -0.1700
Data Index: 5818013 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.5552. Min Act: -0.1700
Data Index: 4596417 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.5239. Min Act: -0.1700
Data Index: 4717856 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.5239. Min Act: -0.1700
Data Index: 3148175 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.4302. Min Act: -0.1700
Data Index: 2647677 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3989. Min Act: -0.1700
Data Index: 8432929 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3989. Min Act: -0.1700
Data Index: 6729691 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3677. Min Act: -0.1700
Data Index: 7406036 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3677. Min Act: -0.1700
Data Index: 8417025 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3989. Min Act: -0.1700
Data Index: 1586157 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3677. Min Act: -0.1700
Data Index: 4415996 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3677. Min Act: -0.1700
Data Index: 6055666 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3364. Min Act: -0.1699
Data Index: 8384170 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3364. Min Act: -0.1700
Data Index: 3566242 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3677. Min Act: -0.1700
Data Index: 7322562 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3052. Min Act: -0.1700
Data Index: 7352965 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3052. Min Act: -0.1700
Data Index: 2650896 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.2739. Min Act: -0.1700
Data Index: 702122 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5864. Min Range: -4.5864
Max Act: 4.3052. Min Act: -0.1700
Data Index: 6665510 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19