Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3070. Min Range: -5.3070
Max Act: 5.3070. Min Act: -0.1700
Data Index: 6475504 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3070. Min Range: -5.3070
Max Act: 5.2445. Min Act: -0.1700
Data Index: 5681700 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3070. Min Range: -5.3070
Max Act: 5.1820. Min Act: -0.1700
Data Index: 620512 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3070. Min Range: -5.3070
Max Act: 5.1195. Min Act: -0.1700
Data Index: 5619814 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3070. Min Range: -5.3070
Max Act: 5.0883. Min Act: -0.1700
Data Index: 6759990 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3070. Min Range: -5.3070
Max Act: 5.0570. Min Act: -0.1700
Data Index: 8228162 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3070. Min Range: -5.3070
Max Act: 5.0258. Min Act: -0.1700
Data Index: 5991634 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.9945. Min Act: -0.1700
Data Index: 7709211 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.9945. Min Act: -0.1700
Data Index: 4574456 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.9945. Min Act: -0.1700
Data Index: 3116276 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.9945. Min Act: -0.1700
Data Index: 6107393 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.9633. Min Act: -0.1700
Data Index: 605840 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.8695. Min Act: -0.1700
Data Index: 8322457 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.9008. Min Act: -0.1700
Data Index: 6300709 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.8383. Min Act: -0.1700
Data Index: 2507945 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.8695. Min Act: -0.1700
Data Index: 3752297 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.8695. Min Act: -0.1700
Data Index: 8313967 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.8070. Min Act: -0.1700
Data Index: 5101531 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.8070. Min Act: -0.1700
Data Index: 1824434 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3070. Min Range: -5.3070
Max Act: 4.8070. Min Act: -0.1700
Data Index: 3752298 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19