Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 134 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2580. Min Range: -5.2580
Max Act: 5.2580. Min Act: -0.1700
Data Index: 1979487 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2580. Min Range: -5.2580
Max Act: 5.2268. Min Act: -0.1700
Data Index: 2240521 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2580. Min Range: -5.2580
Max Act: 5.2268. Min Act: -0.1700
Data Index: 7277220 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2580. Min Range: -5.2580
Max Act: 5.1330. Min Act: -0.1700
Data Index: 7086713 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2580. Min Range: -5.2580
Max Act: 5.0393. Min Act: -0.1700
Data Index: 1846200 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2580. Min Range: -5.2580
Max Act: 5.0393. Min Act: -0.1700
Data Index: 8209008 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2580. Min Range: -5.2580
Max Act: 5.0080. Min Act: -0.1700
Data Index: 5617319 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.9455. Min Act: -0.1700
Data Index: 8039311 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.9455. Min Act: -0.1700
Data Index: 7457587 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.9143. Min Act: -0.1700
Data Index: 7325500 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.9143. Min Act: -0.1700
Data Index: 536334 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.9143. Min Act: -0.1700
Data Index: 3917503 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.9143. Min Act: -0.1700
Data Index: 3112646 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.8830. Min Act: -0.1700
Data Index: 7395612 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.8518. Min Act: -0.1700
Data Index: 1266554 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.8518. Min Act: -0.1700
Data Index: 7745759 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.8205. Min Act: -0.1700
Data Index: 8681132 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.8518. Min Act: -0.1700
Data Index: 1043577 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.8205. Min Act: -0.1700
Data Index: 7125409 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2580. Min Range: -5.2580
Max Act: 4.7893. Min Act: -0.1700
Data Index: 4661835 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19