Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4184. Min Range: -6.4184
Max Act: 6.4184. Min Act: -0.1700
Data Index: 918414 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4184. Min Range: -6.4184
Max Act: 6.0434. Min Act: -0.1700
Data Index: 3402503 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.8559. Min Act: -0.1700
Data Index: 5383321 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.8246. Min Act: -0.1700
Data Index: 4077206 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.8246. Min Act: -0.1700
Data Index: 6582595 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.7934. Min Act: -0.1700
Data Index: 3293432 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6996. Min Act: -0.1700
Data Index: 776005 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6996. Min Act: -0.1700
Data Index: 2090153 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6996. Min Act: -0.1700
Data Index: 2845225 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6996. Min Act: -0.1700
Data Index: 535807 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6684. Min Act: -0.1700
Data Index: 534816 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6684. Min Act: -0.1700
Data Index: 4740897 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6684. Min Act: -0.1700
Data Index: 8058236 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6684. Min Act: -0.1700
Data Index: 4831807 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6684. Min Act: -0.1700
Data Index: 6948782 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6684. Min Act: -0.1700
Data Index: 387252 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6371. Min Act: -0.1700
Data Index: 7108410 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6371. Min Act: -0.1700
Data Index: 1359442 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6059. Min Act: -0.1700
Data Index: 4417596 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4184. Min Range: -6.4184
Max Act: 5.6059. Min Act: -0.1700
Data Index: 5538353 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19