Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1605. Min Range: -8.1605
Max Act: 8.1605. Min Act: -0.1700
Data Index: 6640945 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.9418. Min Act: -0.1700
Data Index: 6401276 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.8793. Min Act: -0.1700
Data Index: 4637677 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.8480. Min Act: -0.1700
Data Index: 4523040 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.7855. Min Act: -0.1700
Data Index: 7245988 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.7543. Min Act: -0.1700
Data Index: 1240934 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.7543. Min Act: -0.1700
Data Index: 4315470 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.7543. Min Act: -0.1700
Data Index: 5465388 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.7230. Min Act: -0.1700
Data Index: 7471780 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.7543. Min Act: -0.1700
Data Index: 8559329 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.6605. Min Act: -0.1700
Data Index: 1213179 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.6605. Min Act: -0.1700
Data Index: 8604357 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.6918. Min Act: -0.1700
Data Index: 1476471 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.6605. Min Act: -0.1700
Data Index: 569346 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.6918. Min Act: -0.1700
Data Index: 5382586 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.6293. Min Act: -0.1700
Data Index: 6912102 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.6605. Min Act: -0.1700
Data Index: 4633812 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.5980. Min Act: -0.1700
Data Index: 2684462 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.5980. Min Act: -0.1700
Data Index: 3639225 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1605. Min Range: -8.1605
Max Act: 7.5980. Min Act: -0.1700
Data Index: 6686707 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19