Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4445 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3348. Min Range: -7.3348
Max Act: 7.3348. Min Act: -0.1700
Data Index: 2035958 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3348. Min Range: -7.3348
Max Act: 7.0223. Min Act: -0.1700
Data Index: 4504628 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.9286. Min Act: -0.1700
Data Index: 5707528 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.8036. Min Act: -0.1700
Data Index: 1934051 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.6473. Min Act: -0.1700
Data Index: 8769776 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.6473. Min Act: -0.1700
Data Index: 404690 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.6161. Min Act: -0.1700
Data Index: 2363749 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.5848. Min Act: -0.1700
Data Index: 1013858 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.4911. Min Act: -0.1700
Data Index: 6975932 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.5223. Min Act: -0.1700
Data Index: 334822 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.4911. Min Act: -0.1700
Data Index: 3167658 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.4598. Min Act: -0.1700
Data Index: 6279780 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.4598. Min Act: -0.1700
Data Index: 7917905 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.4598. Min Act: -0.1700
Data Index: 541978 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.4286. Min Act: -0.1700
Data Index: 668364 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.3973. Min Act: -0.1700
Data Index: 6162289 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.3661. Min Act: -0.1700
Data Index: 2541891 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.3661. Min Act: -0.1700
Data Index: 1748038 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.3661. Min Act: -0.1700
Data Index: 4122155 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3348. Min Range: -7.3348
Max Act: 6.3348. Min Act: -0.1700
Data Index: 6308258 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19