Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1080 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2231. Min Range: -7.2231
Max Act: 7.2231. Min Act: -0.1700
Data Index: 752670 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.7231. Min Act: -0.1700
Data Index: 1570253 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.5668. Min Act: -0.1700
Data Index: 2943119 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.5668. Min Act: -0.1700
Data Index: 1744331 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.4418. Min Act: -0.1700
Data Index: 6985786 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.4418. Min Act: -0.1700
Data Index: 1256335 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.4106. Min Act: -0.1700
Data Index: 1943567 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.4106. Min Act: -0.1700
Data Index: 2379439 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.3168. Min Act: -0.1700
Data Index: 7621736 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.3481. Min Act: -0.1700
Data Index: 6844087 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.3481. Min Act: -0.1700
Data Index: 8005530 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.3168. Min Act: -0.1700
Data Index: 3092526 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.2856. Min Act: -0.1700
Data Index: 2720675 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.3168. Min Act: -0.1700
Data Index: 2859277 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.2856. Min Act: -0.1700
Data Index: 4172148 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.2543. Min Act: -0.1700
Data Index: 4624463 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.2856. Min Act: -0.1700
Data Index: 4866066 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.2856. Min Act: -0.1700
Data Index: 5944535 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.2856. Min Act: -0.1700
Data Index: 4096540 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2231. Min Range: -7.2231
Max Act: 6.2543. Min Act: -0.1700
Data Index: 1020006 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19