Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.4163. Min Act: -0.1700
Data Index: 4926337 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.3538. Min Act: -0.1700
Data Index: 5222035 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.2601. Min Act: -0.1700
Data Index: 4293237 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.2288. Min Act: -0.1700
Data Index: 8427159 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1663. Min Act: -0.1700
Data Index: 5553449 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1663. Min Act: -0.1700
Data Index: 1080856 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1351. Min Act: -0.1700
Data Index: 7738004 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1351. Min Act: -0.1700
Data Index: 61354 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.1038. Min Act: -0.1700
Data Index: 8324935 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0726. Min Act: -0.1700
Data Index: 4047084 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0726. Min Act: -0.1700
Data Index: 8424642 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0726. Min Act: -0.1700
Data Index: 134241 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0726. Min Act: -0.1700
Data Index: 8599115 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0413. Min Act: -0.1700
Data Index: 1516309 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0413. Min Act: -0.1700
Data Index: 3396979 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0413. Min Act: -0.1700
Data Index: 886805 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0413. Min Act: -0.1700
Data Index: 8508301 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0413. Min Act: -0.1700
Data Index: 3605079 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0413. Min Act: -0.1700
Data Index: 6892834 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4163. Min Range: -6.4163
Max Act: 6.0413. Min Act: -0.1700
Data Index: 616695 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19