Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4533 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.9456. Min Act: -0.1700
Data Index: 5630547 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.8206. Min Act: -0.1700
Data Index: 5387713 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.6956. Min Act: -0.1700
Data Index: 1213869 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.6956. Min Act: -0.1700
Data Index: 7841805 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.6331. Min Act: -0.1700
Data Index: 6389284 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.6331. Min Act: -0.1700
Data Index: 1080231 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.6331. Min Act: -0.1700
Data Index: 286282 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.5706. Min Act: -0.1700
Data Index: 4045220 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.5706. Min Act: -0.1700
Data Index: 6223086 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.5081. Min Act: -0.1700
Data Index: 6348652 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.5081. Min Act: -0.1700
Data Index: 148958 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.5081. Min Act: -0.1700
Data Index: 4904605 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.4456. Min Act: -0.1700
Data Index: 152973 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.4456. Min Act: -0.1700
Data Index: 5057823 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.4144. Min Act: -0.1700
Data Index: 8227220 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.4456. Min Act: -0.1700
Data Index: 2077850 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.4456. Min Act: -0.1700
Data Index: 3128061 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.5081. Min Act: -0.1700
Data Index: 2846522 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.5081. Min Act: -0.1700
Data Index: 5057824 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9456. Min Range: -7.9456
Max Act: 7.4144. Min Act: -0.1700
Data Index: 8100328 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19