Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4665 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.9180. Min Act: -0.1700
Data Index: 1331630 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.8085. Min Act: -0.1700
Data Index: 1187616 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.8085. Min Act: -0.1700
Data Index: 3543788 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.7772. Min Act: -0.1700
Data Index: 582770 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.7772. Min Act: -0.1700
Data Index: 747743 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.7460. Min Act: -0.1700
Data Index: 8246743 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.7460. Min Act: -0.1700
Data Index: 1510706 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.7460. Min Act: -0.1700
Data Index: 8567640 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.7303. Min Act: -0.1700
Data Index: 527361 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.7303. Min Act: -0.1700
Data Index: 910477 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.7147. Min Act: -0.1700
Data Index: 571076 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.7147. Min Act: -0.1700
Data Index: 7561990 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.6834. Min Act: -0.1700
Data Index: 4799992 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.6834. Min Act: -0.1700
Data Index: 1239776 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.6677. Min Act: -0.1700
Data Index: 5893440 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.6521. Min Act: -0.1700
Data Index: 1309280 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.6521. Min Act: -0.1700
Data Index: 998152 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.6208. Min Act: -0.1700
Data Index: 4782621 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.6208. Min Act: -0.1700
Data Index: 2114103 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9180. Min Range: -3.9180
Max Act: 3.6208. Min Act: -0.1700
Data Index: 2206703 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19