Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3906 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1416. Min Range: -5.1416
Max Act: 5.1416. Min Act: -0.1700
Data Index: 1143084 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1416. Min Range: -5.1416
Max Act: 5.1104. Min Act: -0.1700
Data Index: 4656573 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.7041. Min Act: -0.1700
Data Index: 7696151 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.6416. Min Act: -0.1700
Data Index: 1275363 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.5791. Min Act: -0.1700
Data Index: 7643291 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.4229. Min Act: -0.1700
Data Index: 6861702 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.3916. Min Act: -0.1700
Data Index: 4455773 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.3916. Min Act: -0.1700
Data Index: 7116612 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.2979. Min Act: -0.1700
Data Index: 1568890 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.3291. Min Act: -0.1700
Data Index: 5661360 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.3291. Min Act: -0.1700
Data Index: 7662116 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.3291. Min Act: -0.1700
Data Index: 2973560 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.2979. Min Act: -0.1700
Data Index: 4312115 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.2979. Min Act: -0.1700
Data Index: 5542630 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.2979. Min Act: -0.1700
Data Index: 8434206 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.2979. Min Act: -0.1700
Data Index: 5245131 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.2979. Min Act: -0.1700
Data Index: 1464606 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.2666. Min Act: -0.1700
Data Index: 4885543 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.2354. Min Act: -0.1700
Data Index: 4955274 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1416. Min Range: -5.1416
Max Act: 4.2666. Min Act: -0.1700
Data Index: 6110102 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19