Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.8272. Min Act: -0.1700
Data Index: 1407580 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.6397. Min Act: -0.1700
Data Index: 6909628 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.6397. Min Act: -0.1700
Data Index: 365902 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.6085. Min Act: -0.1700
Data Index: 274132 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.6085. Min Act: -0.1700
Data Index: 4252989 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.5772. Min Act: -0.1700
Data Index: 6652579 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.5460. Min Act: -0.1700
Data Index: 5762060 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.5460. Min Act: -0.1700
Data Index: 3081362 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.5147. Min Act: -0.1700
Data Index: 7941332 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.5147. Min Act: -0.1700
Data Index: 4232055 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.4835. Min Act: -0.1700
Data Index: 3122300 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.5147. Min Act: -0.1700
Data Index: 3097707 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.4835. Min Act: -0.1700
Data Index: 388992 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.4835. Min Act: -0.1700
Data Index: 1233225 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.4835. Min Act: -0.1700
Data Index: 2803446 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.4835. Min Act: -0.1700
Data Index: 8273392 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.4835. Min Act: -0.1700
Data Index: 5148279 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.4522. Min Act: -0.1700
Data Index: 4841175 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.4522. Min Act: -0.1700
Data Index: 4020474 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8272. Min Range: -4.8272
Max Act: 4.4522. Min Act: -0.1700
Data Index: 4766200 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19