Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.4043. Min Act: -0.1700
Data Index: 4124052 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.2480. Min Act: -0.1700
Data Index: 2997990 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.1230. Min Act: -0.1700
Data Index: 8456610 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.0918. Min Act: -0.1700
Data Index: 2997989 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.0605. Min Act: -0.1700
Data Index: 4785911 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.0605. Min Act: -0.1700
Data Index: 3164705 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.0605. Min Act: -0.1700
Data Index: 8456611 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.0605. Min Act: -0.1700
Data Index: 3374548 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.9980. Min Act: -0.1700
Data Index: 7227921 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.0605. Min Act: -0.1700
Data Index: 3278175 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4043. Min Range: -7.4043
Max Act: 7.0293. Min Act: -0.1700
Data Index: 8094331 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.9668. Min Act: -0.1700
Data Index: 5817782 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.9980. Min Act: -0.1700
Data Index: 6300937 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.9668. Min Act: -0.1700
Data Index: 358920 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.9355. Min Act: -0.1700
Data Index: 3000890 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.9355. Min Act: -0.1700
Data Index: 8540330 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.9043. Min Act: -0.1700
Data Index: 423582 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.9668. Min Act: -0.1700
Data Index: 6137069 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.9043. Min Act: -0.1700
Data Index: 6300938 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4043. Min Range: -7.4043
Max Act: 6.8730. Min Act: -0.1700
Data Index: 4899544 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19