Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4383 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.4202. Min Act: -0.1700
Data Index: 1848790 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3889. Min Act: -0.1700
Data Index: 4922133 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3577. Min Act: -0.1700
Data Index: 8054265 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3577. Min Act: -0.1700
Data Index: 8158446 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3264. Min Act: -0.1700
Data Index: 2903650 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 1839876 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 3034037 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1389. Min Act: -0.1700
Data Index: 6284568 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1389. Min Act: -0.1700
Data Index: 1111117 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1077. Min Act: -0.1700
Data Index: 6640533 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1077. Min Act: -0.1700
Data Index: 5017384 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0764. Min Act: -0.1700
Data Index: 925216 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0764. Min Act: -0.1700
Data Index: 6640520 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0452. Min Act: -0.1700
Data Index: 8623826 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0764. Min Act: -0.1700
Data Index: 8158445 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0452. Min Act: -0.1700
Data Index: 8656584 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0452. Min Act: -0.1700
Data Index: 1588371 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0452. Min Act: -0.1700
Data Index: 3469546 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0139. Min Act: -0.1700
Data Index: 6206001 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.0139. Min Act: -0.1700
Data Index: 3872162 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19