Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1518 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.7599. Min Act: -0.1699
Data Index: 626540 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.6349. Min Act: -0.1700
Data Index: 567141 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.5099. Min Act: -0.1700
Data Index: 8796216 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.3849. Min Act: -0.1700
Data Index: 449331 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.3224. Min Act: -0.1700
Data Index: 3197967 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.2599. Min Act: -0.1700
Data Index: 3035558 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.3224. Min Act: -0.1700
Data Index: 3051581 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.2599. Min Act: -0.1700
Data Index: 666312 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1974. Min Act: -0.1700
Data Index: 3884636 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1974. Min Act: -0.1700
Data Index: 2452173 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1974. Min Act: -0.1700
Data Index: 1609994 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.2599. Min Act: -0.1700
Data Index: 1438345 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1349. Min Act: -0.1700
Data Index: 39564 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1349. Min Act: -0.1700
Data Index: 7515332 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1349. Min Act: -0.1700
Data Index: 6629994 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1349. Min Act: -0.1700
Data Index: 1732962 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1349. Min Act: -0.1700
Data Index: 5806790 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1349. Min Act: -0.1700
Data Index: 5394212 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1349. Min Act: -0.1699
Data Index: 2264912 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7599. Min Range: -9.7599
Max Act: 9.1349. Min Act: -0.1700
Data Index: 5781084 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19