Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1755 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.7272. Min Act: -0.1700
Data Index: 4260981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.6752. Min Act: -0.1700
Data Index: 3914275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.6404. Min Act: -0.1700
Data Index: 3347579 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.6230. Min Act: -0.1700
Data Index: 8474546 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.6055. Min Act: -0.1700
Data Index: 108564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.6055. Min Act: -0.1699
Data Index: 6960325 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.6055. Min Act: -0.1680
Data Index: 1572542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5881. Min Act: -0.1700
Data Index: 8613040 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5881. Min Act: -0.1700
Data Index: 3227399 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5706. Min Act: -0.1700
Data Index: 3329652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.6055. Min Act: -0.1700
Data Index: 1449268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5706. Min Act: -0.1700
Data Index: 2147794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5706. Min Act: -0.1700
Data Index: 5070156 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5355. Min Act: -0.1700
Data Index: 8106064 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5355. Min Act: -0.1697
Data Index: 554205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5355. Min Act: -0.1700
Data Index: 4312113 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5180. Min Act: -0.1700
Data Index: 3063622 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5180. Min Act: -0.1700
Data Index: 2022110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5355. Min Act: -0.1697
Data Index: 6802268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7272. Min Range: -1.7272
Max Act: 1.5005. Min Act: -0.1700
Data Index: 4377462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19