Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3339 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.9182. Min Act: -0.1700
Data Index: 8691366 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.8556. Min Act: -0.1700
Data Index: 8428811 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.8244. Min Act: -0.1700
Data Index: 1384661 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.8244. Min Act: -0.1700
Data Index: 5416770 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.8244. Min Act: -0.1700
Data Index: 4767278 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.7931. Min Act: -0.1700
Data Index: 5159442 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.7618. Min Act: -0.1700
Data Index: 8624987 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.7618. Min Act: -0.1700
Data Index: 2315458 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.7618. Min Act: -0.1700
Data Index: 8825221 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.7305. Min Act: -0.1700
Data Index: 5415856 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.7305. Min Act: -0.1700
Data Index: 8184560 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.7305. Min Act: -0.1700
Data Index: 6643134 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6680. Min Act: -0.1700
Data Index: 138438 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6993. Min Act: -0.1700
Data Index: 2040764 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6680. Min Act: -0.1700
Data Index: 5981211 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6993. Min Act: -0.1700
Data Index: 2859260 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6680. Min Act: -0.1700
Data Index: 2361294 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6993. Min Act: -0.1700
Data Index: 2718539 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6054. Min Act: -0.1700
Data Index: 1744387 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6367. Min Act: -0.1700
Data Index: 1300586 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19