Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1534. Min Range: -3.1534
Max Act: 3.1534. Min Act: -0.1700
Data Index: 3012701 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1534. Min Range: -3.1534
Max Act: 3.1377. Min Act: -0.1700
Data Index: 7295183 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1534. Min Range: -3.1534
Max Act: 3.0589. Min Act: -0.1700
Data Index: 1458486 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1534. Min Range: -3.1534
Max Act: 3.0273. Min Act: -0.1700
Data Index: 2618852 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1534. Min Range: -3.1534
Max Act: 3.0273. Min Act: -0.1700
Data Index: 7939760 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1534. Min Range: -3.1534
Max Act: 3.0273. Min Act: -0.1700
Data Index: 1020944 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1534. Min Range: -3.1534
Max Act: 3.0273. Min Act: -0.1700
Data Index: 8001262 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1534. Min Range: -3.1534
Max Act: 3.0115. Min Act: -0.1700
Data Index: 6220163 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9957. Min Act: -0.1700
Data Index: 7363340 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9641. Min Act: -0.1700
Data Index: 5006439 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9641. Min Act: -0.1700
Data Index: 5177902 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9641. Min Act: -0.1700
Data Index: 6263304 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9324. Min Act: -0.1700
Data Index: 8267183 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9324. Min Act: -0.1700
Data Index: 7765477 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9324. Min Act: -0.1700
Data Index: 3870191 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9324. Min Act: -0.1700
Data Index: 3649363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9324. Min Act: -0.1700
Data Index: 3478351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9324. Min Act: -0.1700
Data Index: 7441519 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9324. Min Act: -0.1700
Data Index: 2653839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1534. Min Range: -3.1534
Max Act: 2.9324. Min Act: -0.1700
Data Index: 3574859 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19