Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.7256. Min Act: -0.1700
Data Index: 1794430 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.7256. Min Act: -0.1700
Data Index: 1881531 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6943. Min Act: -0.1700
Data Index: 1584828 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6943. Min Act: -0.1700
Data Index: 468416 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6318. Min Act: -0.1700
Data Index: 130343 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6318. Min Act: -0.1700
Data Index: 631325 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6318. Min Act: -0.1700
Data Index: 3507893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6318. Min Act: -0.1700
Data Index: 2684089 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6318. Min Act: -0.1700
Data Index: 4803818 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6006. Min Act: -0.1700
Data Index: 7024752 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6006. Min Act: -0.1700
Data Index: 3638602 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6006. Min Act: -0.1700
Data Index: 4800820 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6006. Min Act: -0.1700
Data Index: 3259912 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6006. Min Act: -0.1700
Data Index: 6610181 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6006. Min Act: -0.1700
Data Index: 2436221 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.6006. Min Act: -0.1700
Data Index: 593335 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.5693. Min Act: -0.1700
Data Index: 3563950 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.5693. Min Act: -0.1700
Data Index: 4185700 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.5693. Min Act: -0.1700
Data Index: 4800816 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7256. Min Range: -5.7256
Max Act: 5.5693. Min Act: -0.1700
Data Index: 102452 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19