Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4446. Min Act: -0.1700
Data Index: 2732421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4446. Min Act: -0.1700
Data Index: 3377067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4446. Min Act: -0.1700
Data Index: 1323538 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4132. Min Act: -0.1700
Data Index: 7824353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4132. Min Act: -0.1700
Data Index: 3120835 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4132. Min Act: -0.1700
Data Index: 740320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4132. Min Act: -0.1700
Data Index: 4005724 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4132. Min Act: -0.1700
Data Index: 5142722 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4132. Min Act: -0.1700
Data Index: 4934033 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.4132. Min Act: -0.1700
Data Index: 525451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3819. Min Act: -0.1700
Data Index: 6624091 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3819. Min Act: -0.1700
Data Index: 6171448 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3819. Min Act: -0.1700
Data Index: 5907580 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3819. Min Act: -0.1700
Data Index: 5223845 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3505. Min Act: -0.1700
Data Index: 4731349 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3819. Min Act: -0.1700
Data Index: 4141999 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3819. Min Act: -0.1700
Data Index: 1161544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3819. Min Act: -0.1700
Data Index: 3861840 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3819. Min Act: -0.1700
Data Index: 1069503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4446. Min Range: -3.4446
Max Act: 3.3819. Min Act: -0.1700
Data Index: 3347360 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19