Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3731 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.4394. Min Act: -0.1700
Data Index: 7163595 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.4081. Min Act: -0.1700
Data Index: 347773 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.3924. Min Act: -0.1700
Data Index: 7984733 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.3454. Min Act: -0.1700
Data Index: 6453912 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.2826. Min Act: -0.1700
Data Index: 4810679 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.2669. Min Act: -0.1700
Data Index: 1135426 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.2826. Min Act: -0.1700
Data Index: 8215454 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.2512. Min Act: -0.1700
Data Index: 3004468 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.2040. Min Act: -0.1700
Data Index: 8420028 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.2355. Min Act: -0.1700
Data Index: 1925544 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.2355. Min Act: -0.1700
Data Index: 8606786 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.2197. Min Act: -0.1700
Data Index: 2918238 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.1883. Min Act: -0.1700
Data Index: 8536974 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.1568. Min Act: -0.1700
Data Index: 4971878 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.1568. Min Act: -0.1700
Data Index: 3901043 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.1253. Min Act: -0.1700
Data Index: 7386151 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.1411. Min Act: -0.1700
Data Index: 1987972 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.1411. Min Act: -0.1700
Data Index: 1634764 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.1411. Min Act: -0.1700
Data Index: 4236276 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4394. Min Range: -3.4394
Max Act: 3.1411. Min Act: -0.1700
Data Index: 3154184 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19