Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.3798. Min Act: -0.1700
Data Index: 2795695 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.4110. Min Act: -0.1700
Data Index: 2795684 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.3485. Min Act: -0.1700
Data Index: 1388445 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.2860. Min Act: -0.1700
Data Index: 1312972 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.2860. Min Act: -0.1700
Data Index: 2491363 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.2548. Min Act: -0.1700
Data Index: 5711137 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.2548. Min Act: -0.1700
Data Index: 5990127 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.2235. Min Act: -0.1700
Data Index: 1556656 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.2235. Min Act: -0.1700
Data Index: 6703040 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1610. Min Act: -0.1700
Data Index: 6465580 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1923. Min Act: -0.1700
Data Index: 3721868 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1297. Min Act: -0.1700
Data Index: 7813568 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1610. Min Act: -0.1700
Data Index: 4376690 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1923. Min Act: -0.1700
Data Index: 7696900 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1610. Min Act: -0.1700
Data Index: 8508567 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1610. Min Act: -0.1700
Data Index: 5657608 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1297. Min Act: -0.1700
Data Index: 7451596 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1923. Min Act: -0.1700
Data Index: 2425388 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1297. Min Act: -0.1700
Data Index: 1485672 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4110. Min Range: -4.4110
Max Act: 4.1610. Min Act: -0.1700
Data Index: 361548 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19