Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1420 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0552. Min Range: -5.0552
Max Act: 5.0552. Min Act: -0.1700
Data Index: 674405 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0552. Min Range: -5.0552
Max Act: 5.0240. Min Act: -0.1700
Data Index: 1031533 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0552. Min Range: -5.0552
Max Act: 5.0240. Min Act: -0.1700
Data Index: 3929039 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0552. Min Range: -5.0552
Max Act: 5.0240. Min Act: -0.1700
Data Index: 3929043 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.9927. Min Act: -0.1700
Data Index: 3929038 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.9615. Min Act: -0.1700
Data Index: 4015908 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.9302. Min Act: -0.1700
Data Index: 6820243 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.9302. Min Act: -0.1700
Data Index: 381124 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.9302. Min Act: -0.1700
Data Index: 3929036 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8677. Min Act: -0.1700
Data Index: 381120 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8677. Min Act: -0.1700
Data Index: 1031544 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8677. Min Act: -0.1700
Data Index: 3929034 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8677. Min Act: -0.1700
Data Index: 3929028 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8677. Min Act: -0.1700
Data Index: 3929044 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8677. Min Act: -0.1700
Data Index: 381122 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8677. Min Act: -0.1700
Data Index: 4015903 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8677. Min Act: -0.1700
Data Index: 1031540 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8365. Min Act: -0.1700
Data Index: 1031538 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8677. Min Act: -0.1700
Data Index: 1031543 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0552. Min Range: -5.0552
Max Act: 4.8365. Min Act: -0.1700
Data Index: 1031539 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19