Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4925 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.7543. Min Act: -0.1700
Data Index: 4846398 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.7231. Min Act: -0.1700
Data Index: 650483 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.7231. Min Act: -0.1700
Data Index: 2711846 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6606. Min Act: -0.1700
Data Index: 129318 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6606. Min Act: -0.1700
Data Index: 1764819 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6293. Min Act: -0.1700
Data Index: 8035919 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6293. Min Act: -0.1700
Data Index: 5982465 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5981. Min Act: -0.1700
Data Index: 4521585 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6293. Min Act: -0.1700
Data Index: 131848 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6293. Min Act: -0.1700
Data Index: 4408827 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6293. Min Act: -0.1700
Data Index: 68808 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5981. Min Act: -0.1700
Data Index: 513734 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6293. Min Act: -0.1700
Data Index: 8198540 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5668. Min Act: -0.1700
Data Index: 8336390 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5668. Min Act: -0.1700
Data Index: 1783285 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5668. Min Act: -0.1700
Data Index: 384208 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5668. Min Act: -0.1700
Data Index: 6071154 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5356. Min Act: -0.1700
Data Index: 3733358 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5356. Min Act: -0.1700
Data Index: 1204002 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5043. Min Act: -0.1700
Data Index: 3432024 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19