Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4845. Min Range: -7.4845
Max Act: 7.4845. Min Act: -0.1700
Data Index: 2858040 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4845. Min Range: -7.4845
Max Act: 7.4220. Min Act: -0.1700
Data Index: 8123675 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4845. Min Range: -7.4845
Max Act: 7.4220. Min Act: -0.1700
Data Index: 7095388 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4845. Min Range: -7.4845
Max Act: 7.2345. Min Act: -0.1700
Data Index: 691866 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4845. Min Range: -7.4845
Max Act: 7.2345. Min Act: -0.1700
Data Index: 2740647 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4845. Min Range: -7.4845
Max Act: 7.1407. Min Act: -0.1700
Data Index: 2432 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4845. Min Range: -7.4845
Max Act: 7.0782. Min Act: -0.1700
Data Index: 4009643 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4845. Min Range: -7.4845
Max Act: 7.0157. Min Act: -0.1700
Data Index: 4582257 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.9845. Min Act: -0.1700
Data Index: 3713376 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.9532. Min Act: -0.1700
Data Index: 1108326 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.9532. Min Act: -0.1700
Data Index: 1494966 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.9532. Min Act: -0.1700
Data Index: 2180286 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.9220. Min Act: -0.1700
Data Index: 6186979 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.9220. Min Act: -0.1700
Data Index: 5909434 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.8907. Min Act: -0.1700
Data Index: 4988562 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.8282. Min Act: -0.1700
Data Index: 2387402 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.8595. Min Act: -0.1700
Data Index: 2799301 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.8595. Min Act: -0.1700
Data Index: 8780412 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.7970. Min Act: -0.1700
Data Index: 2523869 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4845. Min Range: -7.4845
Max Act: 6.7970. Min Act: -0.1700
Data Index: 6220915 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19