Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.5646. Min Act: -0.1700
Data Index: 4368257 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.4709. Min Act: -0.1700
Data Index: 7584114 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.4084. Min Act: -0.1700
Data Index: 7773996 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.4084. Min Act: -0.1700
Data Index: 3105565 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.3146. Min Act: -0.1700
Data Index: 4333585 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.2208. Min Act: -0.1700
Data Index: 4409113 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.2208. Min Act: -0.1700
Data Index: 6505002 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.1896. Min Act: -0.1700
Data Index: 6025629 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0958. Min Act: -0.1700
Data Index: 1021117 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.1271. Min Act: -0.1700
Data Index: 2104121 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.1271. Min Act: -0.1700
Data Index: 722026 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0958. Min Act: -0.1700
Data Index: 1554186 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0958. Min Act: -0.1700
Data Index: 4486370 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0958. Min Act: -0.1700
Data Index: 1077950 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0646. Min Act: -0.1700
Data Index: 1104017 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0646. Min Act: -0.1700
Data Index: 5432171 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0333. Min Act: -0.1700
Data Index: 4033863 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0333. Min Act: -0.1700
Data Index: 2051276 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0333. Min Act: -0.1700
Data Index: 3078869 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5646. Min Range: -4.5646
Max Act: 4.0333. Min Act: -0.1700
Data Index: 4114472 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19