Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.3538. Min Act: -0.1700
Data Index: 351258 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.3225. Min Act: -0.1700
Data Index: 8669365 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.3225. Min Act: -0.1700
Data Index: 4879478 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.3225. Min Act: -0.1700
Data Index: 3935589 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.3225. Min Act: -0.1700
Data Index: 7491732 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2600. Min Act: -0.1700
Data Index: 3956035 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2912. Min Act: -0.1700
Data Index: 7128495 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2600. Min Act: -0.1700
Data Index: 1255611 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2912. Min Act: -0.1700
Data Index: 6230969 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2600. Min Act: -0.1700
Data Index: 5834578 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2912. Min Act: -0.1700
Data Index: 580106 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2600. Min Act: -0.1700
Data Index: 7885834 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2600. Min Act: -0.1700
Data Index: 1765241 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2600. Min Act: -0.1700
Data Index: 3008973 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2287. Min Act: -0.1700
Data Index: 6587382 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.1975. Min Act: -0.1700
Data Index: 608437 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2287. Min Act: -0.1700
Data Index: 8057540 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2287. Min Act: -0.1700
Data Index: 5603303 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.2287. Min Act: -0.1700
Data Index: 2191718 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3538. Min Range: -4.3538
Max Act: 4.1975. Min Act: -0.1700
Data Index: 2038409 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19