Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3319. Min Range: -8.3319
Max Act: 8.3319. Min Act: -0.1700
Data Index: 7529829 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.5819. Min Act: -0.1700
Data Index: 6523106 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.5819. Min Act: -0.1700
Data Index: 3508221 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.5194. Min Act: -0.1700
Data Index: 2110879 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.3944. Min Act: -0.1700
Data Index: 2437161 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.3631. Min Act: -0.1700
Data Index: 1483999 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.3631. Min Act: -0.1700
Data Index: 802755 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.3631. Min Act: -0.1700
Data Index: 7794860 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.3319. Min Act: -0.1700
Data Index: 19441 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.3319. Min Act: -0.1700
Data Index: 1868195 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.3319. Min Act: -0.1700
Data Index: 1283953 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.2694. Min Act: -0.1700
Data Index: 889993 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.2069. Min Act: -0.1700
Data Index: 8566785 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.2069. Min Act: -0.1700
Data Index: 4296044 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.2069. Min Act: -0.1700
Data Index: 593617 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.2069. Min Act: -0.1700
Data Index: 2680804 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.1756. Min Act: -0.1700
Data Index: 3090421 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.1756. Min Act: -0.1700
Data Index: 3548830 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.1756. Min Act: -0.1700
Data Index: 3406711 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3319. Min Range: -8.3319
Max Act: 7.1756. Min Act: -0.1700
Data Index: 1242302 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19