Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.3664. Min Act: -0.1700
Data Index: 5866201 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.3352. Min Act: -0.1700
Data Index: 6478342 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.2727. Min Act: -0.1700
Data Index: 5969327 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.2101. Min Act: -0.1700
Data Index: 360278 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.1476. Min Act: -0.1700
Data Index: 4062013 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.1164. Min Act: -0.1700
Data Index: 6510207 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.1164. Min Act: -0.1700
Data Index: 947348 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.1164. Min Act: -0.1700
Data Index: 7211054 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.0851. Min Act: -0.1700
Data Index: 125345 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.0851. Min Act: -0.1700
Data Index: 3212262 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.0539. Min Act: -0.1700
Data Index: 2509002 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.0851. Min Act: -0.1700
Data Index: 841885 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.0539. Min Act: -0.1700
Data Index: 5135099 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.0226. Min Act: -0.1700
Data Index: 4229511 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3664. Min Range: -4.3664
Max Act: 4.0226. Min Act: -0.1700
Data Index: 4134472 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3664. Min Range: -4.3664
Max Act: 3.9913. Min Act: -0.1700
Data Index: 1915341 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3664. Min Range: -4.3664
Max Act: 3.9913. Min Act: -0.1700
Data Index: 6510208 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3664. Min Range: -4.3664
Max Act: 3.9913. Min Act: -0.1700
Data Index: 7211061 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3664. Min Range: -4.3664
Max Act: 3.9913. Min Act: -0.1700
Data Index: 4955351 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3664. Min Range: -4.3664
Max Act: 3.9913. Min Act: -0.1700
Data Index: 4680030 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19