Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.7538. Min Act: -0.1700
Data Index: 8102611 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.6913. Min Act: -0.1700
Data Index: 4689739 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.5663. Min Act: -0.1700
Data Index: 1102042 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.5038. Min Act: -0.1700
Data Index: 6308881 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.5038. Min Act: -0.1700
Data Index: 5931159 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.4100. Min Act: -0.1700
Data Index: 346490 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.3788. Min Act: -0.1700
Data Index: 2643267 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.3475. Min Act: -0.1700
Data Index: 2668626 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.3163. Min Act: -0.1700
Data Index: 2521923 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.3163. Min Act: -0.1700
Data Index: 2264846 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2850. Min Act: -0.1700
Data Index: 4689738 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2850. Min Act: -0.1700
Data Index: 8132596 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2538. Min Act: -0.1700
Data Index: 2011847 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2850. Min Act: -0.1700
Data Index: 613182 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2538. Min Act: -0.1700
Data Index: 4229753 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2538. Min Act: -0.1700
Data Index: 5353324 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2225. Min Act: -0.1700
Data Index: 4426362 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2225. Min Act: -0.1700
Data Index: 1726323 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2225. Min Act: -0.1700
Data Index: 4651469 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7538. Min Range: -6.7538
Max Act: 6.2225. Min Act: -0.1700
Data Index: 6203250 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19