Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.2300. Min Act: -0.1700
Data Index: 3131416 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.2300. Min Act: -0.1700
Data Index: 8824065 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.1198. Min Act: -0.1700
Data Index: 6936162 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.1198. Min Act: -0.1700
Data Index: 2169933 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.0883. Min Act: -0.1700
Data Index: 3828886 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.0568. Min Act: -0.1700
Data Index: 8428437 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.0568. Min Act: -0.1700
Data Index: 2556508 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2300. Min Range: -3.2300
Max Act: 2.9936. Min Act: -0.1700
Data Index: 22038 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.0410. Min Act: -0.1700
Data Index: 436232 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.0094. Min Act: -0.1700
Data Index: 2274182 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.0094. Min Act: -0.1700
Data Index: 1099500 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2300. Min Range: -3.2300
Max Act: 2.9936. Min Act: -0.1700
Data Index: 6283257 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2300. Min Range: -3.2300
Max Act: 3.0094. Min Act: -0.1700
Data Index: 6106942 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2300. Min Range: -3.2300
Max Act: 2.9461. Min Act: -0.1700
Data Index: 4331381 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2300. Min Range: -3.2300
Max Act: 2.9461. Min Act: -0.1700
Data Index: 6421348 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2300. Min Range: -3.2300
Max Act: 2.9620. Min Act: -0.1700
Data Index: 2425279 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2300. Min Range: -3.2300
Max Act: 2.9303. Min Act: -0.1700
Data Index: 427351 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2300. Min Range: -3.2300
Max Act: 2.9144. Min Act: -0.1700
Data Index: 764508 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2300. Min Range: -3.2300
Max Act: 2.9144. Min Act: -0.1700
Data Index: 7893320 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2300. Min Range: -3.2300
Max Act: 2.9303. Min Act: -0.1700
Data Index: 1665421 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19