Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4212 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0199. Min Range: -7.0199
Max Act: 7.0199. Min Act: -0.1700
Data Index: 1932694 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.9887. Min Act: -0.1700
Data Index: 704402 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.7699. Min Act: -0.1700
Data Index: 6054671 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.7699. Min Act: -0.1700
Data Index: 7071286 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.7387. Min Act: -0.1700
Data Index: 4708726 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.6762. Min Act: -0.1700
Data Index: 574419 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.6449. Min Act: -0.1700
Data Index: 1164709 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.5824. Min Act: -0.1700
Data Index: 7444046 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.5824. Min Act: -0.1700
Data Index: 1336839 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.5512. Min Act: -0.1700
Data Index: 5936122 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.5512. Min Act: -0.1700
Data Index: 6309350 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.5512. Min Act: -0.1700
Data Index: 4861818 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4887. Min Act: -0.1700
Data Index: 128460 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4887. Min Act: -0.1700
Data Index: 1117815 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4887. Min Act: -0.1700
Data Index: 2854892 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4574. Min Act: -0.1700
Data Index: 1941726 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4574. Min Act: -0.1700
Data Index: 7280361 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.3949. Min Act: -0.1700
Data Index: 5446743 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4262. Min Act: -0.1700
Data Index: 4670188 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4262. Min Act: -0.1700
Data Index: 2894951 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19