Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3095 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.7899. Min Act: -0.1700
Data Index: 8588187 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.7586. Min Act: -0.1700
Data Index: 6939356 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.6961. Min Act: -0.1700
Data Index: 4351736 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.6648. Min Act: -0.1700
Data Index: 5122906 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.6335. Min Act: -0.1700
Data Index: 4937499 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.6335. Min Act: -0.1700
Data Index: 8523803 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.6335. Min Act: -0.1700
Data Index: 7857857 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.6335. Min Act: -0.1700
Data Index: 8464775 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.5865. Min Act: -0.1700
Data Index: 5098095 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.5396. Min Act: -0.1700
Data Index: 2805315 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.5396. Min Act: -0.1700
Data Index: 2210413 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.5396. Min Act: -0.1700
Data Index: 276568 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.5239. Min Act: -0.1700
Data Index: 6030606 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.4926. Min Act: -0.1700
Data Index: 3289208 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.4769. Min Act: -0.1700
Data Index: 3579415 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.4612. Min Act: -0.1700
Data Index: 747610 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.4612. Min Act: -0.1700
Data Index: 1188777 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.4612. Min Act: -0.1700
Data Index: 8054915 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.4456. Min Act: -0.1700
Data Index: 4296528 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7899. Min Range: -3.7899
Max Act: 3.4456. Min Act: -0.1700
Data Index: 4942514 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19