Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.4670. Min Act: -0.1700
Data Index: 8824632 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.4983. Min Act: -0.1700
Data Index: 3711329 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.4670. Min Act: -0.1700
Data Index: 2459478 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.4670. Min Act: -0.1700
Data Index: 1100417 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.4670. Min Act: -0.1700
Data Index: 4079941 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.4358. Min Act: -0.1700
Data Index: 3783482 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.3733. Min Act: -0.1700
Data Index: 3361492 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.3733. Min Act: -0.1700
Data Index: 4763846 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.3733. Min Act: -0.1700
Data Index: 3905968 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.3733. Min Act: -0.1700
Data Index: 2680759 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.3420. Min Act: -0.1700
Data Index: 2450071 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.3420. Min Act: -0.1700
Data Index: 7885292 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.3108. Min Act: -0.1700
Data Index: 5455276 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.2795. Min Act: -0.1700
Data Index: 4849380 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.3108. Min Act: -0.1700
Data Index: 6190090 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.2483. Min Act: -0.1700
Data Index: 2321960 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.2795. Min Act: -0.1700
Data Index: 1794394 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.2795. Min Act: -0.1700
Data Index: 5613708 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.2795. Min Act: -0.1700
Data Index: 5041909 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4983. Min Range: -4.4983
Max Act: 4.2795. Min Act: -0.1700
Data Index: 2122484 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19