Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.9472. Min Act: -0.1700
Data Index: 394511 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.8847. Min Act: -0.1700
Data Index: 4190804 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.7597. Min Act: -0.1700
Data Index: 3726902 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.6347. Min Act: -0.1700
Data Index: 1120489 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.5722. Min Act: -0.1700
Data Index: 5380821 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.6659. Min Act: -0.1700
Data Index: 488702 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.6347. Min Act: -0.1700
Data Index: 5865605 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.5722. Min Act: -0.1700
Data Index: 8395337 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.5722. Min Act: -0.1700
Data Index: 8547814 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.5097. Min Act: -0.1700
Data Index: 3436890 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.5409. Min Act: -0.1700
Data Index: 7437256 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.5409. Min Act: -0.1700
Data Index: 1442604 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.4784. Min Act: -0.1700
Data Index: 448291 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.4784. Min Act: -0.1700
Data Index: 4470396 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.4784. Min Act: -0.1700
Data Index: 5229405 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.4784. Min Act: -0.1700
Data Index: 1373968 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.4784. Min Act: -0.1700
Data Index: 7639105 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.4784. Min Act: -0.1700
Data Index: 8214477 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.4472. Min Act: -0.1700
Data Index: 2878232 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9472. Min Range: -5.9472
Max Act: 5.4472. Min Act: -0.1700
Data Index: 8275548 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19