Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 255 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.2020. Min Act: -0.1700
Data Index: 1100476 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.2020. Min Act: -0.1700
Data Index: 660000 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.2020. Min Act: -0.1700
Data Index: 6520324 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.2020. Min Act: -0.1700
Data Index: 6126223 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.2020. Min Act: -0.1700
Data Index: 2030602 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.2333. Min Act: -0.1700
Data Index: 3001722 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.2020. Min Act: -0.1700
Data Index: 7937106 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.2020. Min Act: -0.1700
Data Index: 804704 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1708. Min Act: -0.1700
Data Index: 3457142 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.2020. Min Act: -0.1700
Data Index: 6998924 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1395. Min Act: -0.1700
Data Index: 480652 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1708. Min Act: -0.1700
Data Index: 3915241 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1708. Min Act: -0.1700
Data Index: 7208782 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1395. Min Act: -0.1700
Data Index: 527055 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1708. Min Act: -0.1700
Data Index: 4819733 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1708. Min Act: -0.1700
Data Index: 3293999 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1395. Min Act: -0.1700
Data Index: 4037375 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1395. Min Act: -0.1700
Data Index: 5007183 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1083. Min Act: -0.1700
Data Index: 5724696 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2333. Min Range: -4.2333
Max Act: 4.1083. Min Act: -0.1700
Data Index: 6198310 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19