Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.7555. Min Act: -0.1700
Data Index: 6589885 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.7243. Min Act: -0.1699
Data Index: 8696517 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.5368. Min Act: -0.1700
Data Index: 2447284 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.5055. Min Act: -0.1700
Data Index: 7762229 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.4743. Min Act: -0.1700
Data Index: 2545893 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.4430. Min Act: -0.1699
Data Index: 4057973 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.4430. Min Act: -0.1700
Data Index: 4055224 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.4743. Min Act: -0.1700
Data Index: 906569 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.4118. Min Act: -0.1700
Data Index: 6645984 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3805. Min Act: -0.1700
Data Index: 4577525 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3805. Min Act: -0.1700
Data Index: 3443826 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3493. Min Act: -0.1700
Data Index: 58855 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3805. Min Act: -0.1699
Data Index: 7048840 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3493. Min Act: -0.1700
Data Index: 8319023 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3493. Min Act: -0.1700
Data Index: 414449 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3493. Min Act: -0.1700
Data Index: 6023811 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3180. Min Act: -0.1700
Data Index: 3443825 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3180. Min Act: -0.1699
Data Index: 1854989 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3180. Min Act: -0.1700
Data Index: 8120630 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7555. Min Range: -5.7555
Max Act: 5.3180. Min Act: -0.1700
Data Index: 6986386 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19