Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 867 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.4450. Min Act: -0.1700
Data Index: 8076882 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.3513. Min Act: -0.1700
Data Index: 7791967 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.1950. Min Act: -0.1700
Data Index: 88883 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.1325. Min Act: -0.1700
Data Index: 7019666 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.0700. Min Act: -0.1700
Data Index: 4905927 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4450. Min Range: -6.4450
Max Act: 6.0075. Min Act: -0.1700
Data Index: 3999290 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9763. Min Act: -0.1700
Data Index: 6058946 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9763. Min Act: -0.1700
Data Index: 1538568 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9138. Min Act: -0.1700
Data Index: 3062478 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9138. Min Act: -0.1700
Data Index: 7725724 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9138. Min Act: -0.1700
Data Index: 7828177 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8825. Min Act: -0.1700
Data Index: 8488280 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.9138. Min Act: -0.1700
Data Index: 1369116 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8825. Min Act: -0.1700
Data Index: 976593 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8825. Min Act: -0.1700
Data Index: 4376566 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8513. Min Act: -0.1700
Data Index: 6775389 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8200. Min Act: -0.1700
Data Index: 6526216 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8513. Min Act: -0.1700
Data Index: 5932776 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8200. Min Act: -0.1700
Data Index: 1148892 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4450. Min Range: -6.4450
Max Act: 5.8200. Min Act: -0.1700
Data Index: 767538 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19