Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.6166. Min Act: -0.1700
Data Index: 3337563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.6166. Min Act: -0.1700
Data Index: 2996789 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5854. Min Act: -0.1700
Data Index: 8747612 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5854. Min Act: -0.1700
Data Index: 2113758 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5541. Min Act: -0.1700
Data Index: 526464 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5541. Min Act: -0.1699
Data Index: 961601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5229. Min Act: -0.1700
Data Index: 7206084 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5229. Min Act: -0.1700
Data Index: 3232734 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5229. Min Act: -0.1700
Data Index: 4478892 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5229. Min Act: -0.1700
Data Index: 7037354 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5229. Min Act: -0.1700
Data Index: 3031802 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5229. Min Act: -0.1700
Data Index: 5283368 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.5229. Min Act: -0.1700
Data Index: 4681150 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.4916. Min Act: -0.1700
Data Index: 7206085 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.4916. Min Act: -0.1700
Data Index: 8043190 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.4916. Min Act: -0.1700
Data Index: 1262702 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.4916. Min Act: -0.1700
Data Index: 3184798 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.4916. Min Act: -0.1700
Data Index: 6299517 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.4916. Min Act: -0.1700
Data Index: 1340319 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6166. Min Range: -4.6166
Max Act: 4.4916. Min Act: -0.1700
Data Index: 6116523 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19