Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4172 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1624. Min Range: -6.1624
Max Act: 6.1624. Min Act: -0.1700
Data Index: 7882237 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1624. Min Range: -6.1624
Max Act: 6.0062. Min Act: -0.1700
Data Index: 6083863 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.8812. Min Act: -0.1700
Data Index: 422879 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.8499. Min Act: -0.1700
Data Index: 3761480 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.8499. Min Act: -0.1700
Data Index: 5248323 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.7874. Min Act: -0.1700
Data Index: 5526335 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.7874. Min Act: -0.1700
Data Index: 4309945 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.7562. Min Act: -0.1700
Data Index: 5615056 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.7562. Min Act: -0.1700
Data Index: 4606534 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.7562. Min Act: -0.1700
Data Index: 1736798 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.7562. Min Act: -0.1700
Data Index: 7966000 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.7249. Min Act: -0.1700
Data Index: 1486811 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.7249. Min Act: -0.1700
Data Index: 2241320 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.7249. Min Act: -0.1700
Data Index: 8292955 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.6937. Min Act: -0.1700
Data Index: 5736733 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.6937. Min Act: -0.1700
Data Index: 4570370 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.6624. Min Act: -0.1700
Data Index: 4726679 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.6312. Min Act: -0.1700
Data Index: 3069644 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.5999. Min Act: -0.1700
Data Index: 8389347 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.5999. Min Act: -0.1700
Data Index: 3816467 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19