Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2151 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.2103. Min Act: -0.1700
Data Index: 3275337 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.2103. Min Act: -0.1700
Data Index: 3225300 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.1791. Min Act: -0.1700
Data Index: 953851 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.1166. Min Act: -0.1700
Data Index: 2238331 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.1166. Min Act: -0.1700
Data Index: 7410091 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.0853. Min Act: -0.1700
Data Index: 8523464 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.0853. Min Act: -0.1700
Data Index: 3972979 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.0228. Min Act: -0.1700
Data Index: 3921869 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.0228. Min Act: -0.1700
Data Index: 6777230 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2103. Min Range: -5.2103
Max Act: 5.0541. Min Act: -0.1700
Data Index: 3220137 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.9916. Min Act: -0.1700
Data Index: 6796368 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.9916. Min Act: -0.1700
Data Index: 2348027 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.9291. Min Act: -0.1700
Data Index: 4385300 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.9603. Min Act: -0.1700
Data Index: 584824 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.9603. Min Act: -0.1700
Data Index: 7767068 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.9291. Min Act: -0.1700
Data Index: 7203158 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.9291. Min Act: -0.1700
Data Index: 2959635 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.8978. Min Act: -0.1700
Data Index: 5003558 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.9291. Min Act: -0.1700
Data Index: 6796364 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2103. Min Range: -5.2103
Max Act: 4.9291. Min Act: -0.1700
Data Index: 6745058 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19