Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3342. Min Range: -5.3342
Max Act: 5.3342. Min Act: -0.1700
Data Index: 2000191 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3342. Min Range: -5.3342
Max Act: 5.2717. Min Act: -0.1700
Data Index: 1196843 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.9279. Min Act: -0.1700
Data Index: 1601202 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.8654. Min Act: -0.1700
Data Index: 3569109 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.8654. Min Act: -0.1700
Data Index: 4125757 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.8342. Min Act: -0.1700
Data Index: 2792056 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.8029. Min Act: -0.1700
Data Index: 8821890 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7717. Min Act: -0.1700
Data Index: 6681805 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7404. Min Act: -0.1700
Data Index: 6615415 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7717. Min Act: -0.1700
Data Index: 3261701 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7404. Min Act: -0.1700
Data Index: 5825641 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7404. Min Act: -0.1700
Data Index: 8685037 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7092. Min Act: -0.1700
Data Index: 7147592 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7092. Min Act: -0.1700
Data Index: 8238211 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7092. Min Act: -0.1700
Data Index: 6800724 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7092. Min Act: -0.1700
Data Index: 847232 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7092. Min Act: -0.1700
Data Index: 5047229 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7092. Min Act: -0.1700
Data Index: 4456627 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7092. Min Act: -0.1700
Data Index: 7914599 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3342. Min Range: -5.3342
Max Act: 4.7092. Min Act: -0.1700
Data Index: 7394919 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19