Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5017 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.4864. Min Act: -0.1700
Data Index: 4777705 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.2989. Min Act: -0.1700
Data Index: 3534924 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.2677. Min Act: -0.1700
Data Index: 8298431 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.2364. Min Act: -0.1700
Data Index: 266838 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.2364. Min Act: -0.1700
Data Index: 2280301 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.2052. Min Act: -0.1700
Data Index: 795177 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.1739. Min Act: -0.1700
Data Index: 5441578 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.1739. Min Act: -0.1700
Data Index: 7327072 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.1739. Min Act: -0.1700
Data Index: 8547297 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.1114. Min Act: -0.1700
Data Index: 2282542 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.1427. Min Act: -0.1700
Data Index: 2572422 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.0802. Min Act: -0.1700
Data Index: 7332332 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.0802. Min Act: -0.1700
Data Index: 1010846 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.0802. Min Act: -0.1700
Data Index: 3567351 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.0489. Min Act: -0.1700
Data Index: 8790931 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.0489. Min Act: -0.1700
Data Index: 4921885 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.0177. Min Act: -0.1700
Data Index: 527618 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.0177. Min Act: -0.1700
Data Index: 6273950 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.0177. Min Act: -0.1700
Data Index: 8211514 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4864. Min Range: -5.4864
Max Act: 5.0177. Min Act: -0.1700
Data Index: 7108595 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19