Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4475 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.8422. Min Act: -0.1700
Data Index: 1016308 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.8110. Min Act: -0.1700
Data Index: 6210250 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.7797. Min Act: -0.1700
Data Index: 2355735 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.7797. Min Act: -0.1700
Data Index: 5593348 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.7172. Min Act: -0.1700
Data Index: 6212824 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.7172. Min Act: -0.1700
Data Index: 1721270 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.6547. Min Act: -0.1700
Data Index: 6059800 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.6547. Min Act: -0.1700
Data Index: 479519 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.6547. Min Act: -0.1700
Data Index: 2487369 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.6235. Min Act: -0.1700
Data Index: 3656939 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5922. Min Act: -0.1700
Data Index: 3720044 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5922. Min Act: -0.1700
Data Index: 2183741 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5610. Min Act: -0.1700
Data Index: 3784874 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5610. Min Act: -0.1700
Data Index: 227105 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5922. Min Act: -0.1700
Data Index: 5474555 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5922. Min Act: -0.1700
Data Index: 4442112 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5610. Min Act: -0.1700
Data Index: 6874332 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5610. Min Act: -0.1700
Data Index: 1795300 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5610. Min Act: -0.1700
Data Index: 8171672 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8422. Min Range: -5.8422
Max Act: 5.5610. Min Act: -0.1700
Data Index: 1016307 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19