Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1191 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1768. Min Range: -5.1768
Max Act: 5.1768. Min Act: -0.1700
Data Index: 480031 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1768. Min Range: -5.1768
Max Act: 5.1143. Min Act: -0.1700
Data Index: 2059460 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1768. Min Range: -5.1768
Max Act: 5.0830. Min Act: -0.1700
Data Index: 2826217 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1768. Min Range: -5.1768
Max Act: 5.1143. Min Act: -0.1700
Data Index: 5424709 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1768. Min Range: -5.1768
Max Act: 5.0830. Min Act: -0.1700
Data Index: 5569725 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1768. Min Range: -5.1768
Max Act: 5.0518. Min Act: -0.1700
Data Index: 1021329 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.9893. Min Act: -0.1700
Data Index: 4653707 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.9580. Min Act: -0.1700
Data Index: 918872 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.9268. Min Act: -0.1700
Data Index: 4010803 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8955. Min Act: -0.1700
Data Index: 6512209 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8955. Min Act: -0.1700
Data Index: 6516774 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8955. Min Act: -0.1700
Data Index: 476913 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8643. Min Act: -0.1700
Data Index: 4826776 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8643. Min Act: -0.1700
Data Index: 4466807 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8643. Min Act: -0.1700
Data Index: 4811953 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8330. Min Act: -0.1700
Data Index: 7484431 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8018. Min Act: -0.1700
Data Index: 5894914 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8018. Min Act: -0.1700
Data Index: 4341792 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8330. Min Act: -0.1700
Data Index: 3488742 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1768. Min Range: -5.1768
Max Act: 4.8018. Min Act: -0.1700
Data Index: 3352342 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19