Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6594. Min Range: -7.6594
Max Act: 7.6594. Min Act: -0.1700
Data Index: 2774497 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6594. Min Range: -7.6594
Max Act: 7.2531. Min Act: -0.1700
Data Index: 8111702 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6594. Min Range: -7.6594
Max Act: 7.1281. Min Act: -0.1700
Data Index: 5374772 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6594. Min Range: -7.6594
Max Act: 7.0656. Min Act: -0.1700
Data Index: 1865549 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.9406. Min Act: -0.1700
Data Index: 1117929 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.9094. Min Act: -0.1700
Data Index: 2301590 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.9094. Min Act: -0.1700
Data Index: 7476120 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.9094. Min Act: -0.1700
Data Index: 4542539 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.8469. Min Act: -0.1700
Data Index: 4951314 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.8156. Min Act: -0.1700
Data Index: 606451 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.8469. Min Act: -0.1700
Data Index: 3293707 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.8156. Min Act: -0.1700
Data Index: 8405779 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.7844. Min Act: -0.1700
Data Index: 6975962 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.8156. Min Act: -0.1700
Data Index: 7822883 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.8156. Min Act: -0.1700
Data Index: 2946929 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.7844. Min Act: -0.1700
Data Index: 6301291 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.7531. Min Act: -0.1700
Data Index: 5052426 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.7219. Min Act: -0.1700
Data Index: 2647261 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.7219. Min Act: -0.1700
Data Index: 7019266 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6594. Min Range: -7.6594
Max Act: 6.7219. Min Act: -0.1700
Data Index: 6020804 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19