Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.7380. Min Act: -0.1700
Data Index: 5300777 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.6442. Min Act: -0.1700
Data Index: 8588878 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.6442. Min Act: -0.1700
Data Index: 749746 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.6129. Min Act: -0.1700
Data Index: 835281 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5972. Min Act: -0.1700
Data Index: 8722832 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.6129. Min Act: -0.1700
Data Index: 7876292 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5972. Min Act: -0.1700
Data Index: 7062471 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5816. Min Act: -0.1700
Data Index: 6880803 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5503. Min Act: -0.1700
Data Index: 3821240 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5189. Min Act: -0.1700
Data Index: 3522570 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5189. Min Act: -0.1700
Data Index: 970923 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5346. Min Act: -0.1700
Data Index: 2333569 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5189. Min Act: -0.1700
Data Index: 3446422 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5346. Min Act: -0.1700
Data Index: 7918799 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5189. Min Act: -0.1700
Data Index: 7213285 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5189. Min Act: -0.1700
Data Index: 7842310 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5346. Min Act: -0.1700
Data Index: 63999 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5033. Min Act: -0.1700
Data Index: 7957831 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5033. Min Act: -0.1700
Data Index: 7324187 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7380. Min Range: -3.7380
Max Act: 3.5189. Min Act: -0.1700
Data Index: 6083123 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19