Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.8647. Min Act: -0.1700
Data Index: 6432094 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.7085. Min Act: -0.1700
Data Index: 2446924 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.6772. Min Act: -0.1700
Data Index: 5866588 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.5835. Min Act: -0.1700
Data Index: 3452715 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.5210. Min Act: -0.1700
Data Index: 6841956 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.5522. Min Act: -0.1700
Data Index: 3286384 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.5210. Min Act: -0.1700
Data Index: 1698073 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4897. Min Act: -0.1700
Data Index: 4609167 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4897. Min Act: -0.1700
Data Index: 1862212 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4897. Min Act: -0.1700
Data Index: 7837975 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4585. Min Act: -0.1700
Data Index: 2598639 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4272. Min Act: -0.1700
Data Index: 7522002 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4272. Min Act: -0.1700
Data Index: 6617370 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4585. Min Act: -0.1700
Data Index: 4311816 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4585. Min Act: -0.1700
Data Index: 4223359 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4272. Min Act: -0.1700
Data Index: 3658509 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.3960. Min Act: -0.1700
Data Index: 412354 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4272. Min Act: -0.1700
Data Index: 8477920 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4272. Min Act: -0.1700
Data Index: 3325239 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8647. Min Range: -6.8647
Max Act: 6.4585. Min Act: -0.1700
Data Index: 5104191 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19