Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3345 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.9846. Min Act: -0.1700
Data Index: 6904686 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 6701117 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 5094523 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 2696198 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6096. Min Act: -0.1700
Data Index: 6809297 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 6304973 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.5471. Min Act: -0.1700
Data Index: 2666829 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.5471. Min Act: -0.1700
Data Index: 3127055 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.4846. Min Act: -0.1700
Data Index: 381322 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.4846. Min Act: -0.1700
Data Index: 7368723 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.4221. Min Act: -0.1700
Data Index: 5097313 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.4221. Min Act: -0.1700
Data Index: 7427269 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.4221. Min Act: -0.1700
Data Index: 390493 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.2971. Min Act: -0.1700
Data Index: 4858821 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.2971. Min Act: -0.1700
Data Index: 51930 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.1721. Min Act: -0.1700
Data Index: 164185 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.2346. Min Act: -0.1700
Data Index: 2602080 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.2346. Min Act: -0.1700
Data Index: 2067516 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.1721. Min Act: -0.1700
Data Index: 5841855 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.1721. Min Act: -0.1700
Data Index: 4534293 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19