Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 607 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.3092. Min Act: -0.1700
Data Index: 1250409 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.2154. Min Act: -0.1700
Data Index: 7906401 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.1842. Min Act: -0.1700
Data Index: 2691550 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.1217. Min Act: -0.1700
Data Index: 7259733 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0904. Min Act: -0.1700
Data Index: 8682997 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3092. Min Range: -6.3092
Max Act: 6.0279. Min Act: -0.1700
Data Index: 4177425 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9967. Min Act: -0.1700
Data Index: 49316 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9967. Min Act: -0.1700
Data Index: 2680013 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9967. Min Act: -0.1700
Data Index: 5765662 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9967. Min Act: -0.1700
Data Index: 6937311 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9654. Min Act: -0.1700
Data Index: 8666626 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9654. Min Act: -0.1700
Data Index: 4893365 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9654. Min Act: -0.1700
Data Index: 6379348 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9342. Min Act: -0.1700
Data Index: 6937310 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9342. Min Act: -0.1700
Data Index: 8519989 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9342. Min Act: -0.1700
Data Index: 5927334 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.9029. Min Act: -0.1700
Data Index: 8672854 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.8717. Min Act: -0.1700
Data Index: 4490317 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.8717. Min Act: -0.1700
Data Index: 5423031 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3092. Min Range: -6.3092
Max Act: 5.8717. Min Act: -0.1700
Data Index: 4676752 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19