Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.3552. Min Act: -0.1700
Data Index: 7710595 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.2927. Min Act: -0.1700
Data Index: 6951954 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1989. Min Act: -0.1700
Data Index: 1928720 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1989. Min Act: -0.1700
Data Index: 6755231 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1989. Min Act: -0.1700
Data Index: 5314471 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1989. Min Act: -0.1700
Data Index: 4329487 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1052. Min Act: -0.1700
Data Index: 4062194 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1052. Min Act: -0.1700
Data Index: 7376120 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.1052. Min Act: -0.1700
Data Index: 3290342 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0739. Min Act: -0.1700
Data Index: 5221437 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0739. Min Act: -0.1700
Data Index: 1326235 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0739. Min Act: -0.1700
Data Index: 693637 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0739. Min Act: -0.1700
Data Index: 4640938 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0739. Min Act: -0.1700
Data Index: 6743130 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0114. Min Act: -0.1700
Data Index: 4536617 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0427. Min Act: -0.1700
Data Index: 6049677 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9802. Min Act: -0.1700
Data Index: 202233 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3552. Min Range: -5.3552
Max Act: 5.0114. Min Act: -0.1700
Data Index: 2393562 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9802. Min Act: -0.1700
Data Index: 2726920 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3552. Min Range: -5.3552
Max Act: 4.9489. Min Act: -0.1700
Data Index: 5919548 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19