Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2296 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.3161. Min Act: -0.1700
Data Index: 5609185 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.2536. Min Act: -0.1700
Data Index: 3294286 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.0661. Min Act: -0.1700
Data Index: 6092484 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3161. Min Range: -7.3161
Max Act: 7.0661. Min Act: -0.1700
Data Index: 8552013 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.9098. Min Act: -0.1700
Data Index: 844002 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.8473. Min Act: -0.1700
Data Index: 8659678 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.9098. Min Act: -0.1700
Data Index: 591157 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7848. Min Act: -0.1700
Data Index: 990658 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7536. Min Act: -0.1700
Data Index: 3265535 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7223. Min Act: -0.1700
Data Index: 6159583 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.7223. Min Act: -0.1700
Data Index: 8010131 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.6598. Min Act: -0.1700
Data Index: 5712069 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.6598. Min Act: -0.1700
Data Index: 6696522 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.5973. Min Act: -0.1700
Data Index: 7707675 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.5973. Min Act: -0.1700
Data Index: 7029593 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.5973. Min Act: -0.1700
Data Index: 8292649 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.6286. Min Act: -0.1700
Data Index: 2144902 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.6286. Min Act: -0.1700
Data Index: 4601254 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.5973. Min Act: -0.1700
Data Index: 6392596 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3161. Min Range: -7.3161
Max Act: 6.5973. Min Act: -0.1700
Data Index: 6955077 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19