Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2932 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.9374. Min Act: -0.1700
Data Index: 8626139 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.8436. Min Act: -0.1700
Data Index: 771943 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.8280. Min Act: -0.1700
Data Index: 3496246 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.8592. Min Act: -0.1700
Data Index: 7298794 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.8436. Min Act: -0.1700
Data Index: 7524359 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.8280. Min Act: -0.1700
Data Index: 3346572 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7967. Min Act: -0.1700
Data Index: 82700 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.8123. Min Act: -0.1700
Data Index: 7609979 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7967. Min Act: -0.1700
Data Index: 3753438 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7654. Min Act: -0.1700
Data Index: 2628643 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7341. Min Act: -0.1700
Data Index: 646990 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7341. Min Act: -0.1700
Data Index: 7236275 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7498. Min Act: -0.1700
Data Index: 4786089 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7498. Min Act: -0.1700
Data Index: 4120989 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7028. Min Act: -0.1700
Data Index: 4394665 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7028. Min Act: -0.1700
Data Index: 3241966 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7185. Min Act: -0.1700
Data Index: 5975977 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.6872. Min Act: -0.1700
Data Index: 7699943 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7185. Min Act: -0.1700
Data Index: 6750665 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9374. Min Range: -3.9374
Max Act: 3.7185. Min Act: -0.1700
Data Index: 3575773 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19