Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5109. Min Range: -9.5109
Max Act: 9.5109. Min Act: -0.1700
Data Index: 6376368 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5109. Min Range: -9.5109
Max Act: 9.3859. Min Act: -0.1700
Data Index: 435573 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5109. Min Range: -9.5109
Max Act: 9.1984. Min Act: -0.1700
Data Index: 4281468 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5109. Min Range: -9.5109
Max Act: 9.0109. Min Act: -0.1700
Data Index: 8058423 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5109. Min Range: -9.5109
Max Act: 9.0109. Min Act: -0.1700
Data Index: 6071273 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5109. Min Range: -9.5109
Max Act: 9.0109. Min Act: -0.1700
Data Index: 6929539 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5109. Min Range: -9.5109
Max Act: 9.0109. Min Act: -0.1700
Data Index: 6307682 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.8859. Min Act: -0.1700
Data Index: 3149202 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.8859. Min Act: -0.1700
Data Index: 3476305 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.8859. Min Act: -0.1700
Data Index: 3624986 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.8859. Min Act: -0.1700
Data Index: 2201150 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.8859. Min Act: -0.1700
Data Index: 8461525 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.8234. Min Act: -0.1700
Data Index: 937719 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.8859. Min Act: -0.1700
Data Index: 3097395 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.8234. Min Act: -0.1700
Data Index: 6118277 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.7609. Min Act: -0.1700
Data Index: 3392076 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.7609. Min Act: -0.1700
Data Index: 1946136 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.7609. Min Act: -0.1700
Data Index: 660302 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.7609. Min Act: -0.1700
Data Index: 1063877 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5109. Min Range: -9.5109
Max Act: 8.7609. Min Act: -0.1700
Data Index: 3780646 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19