Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1609 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0499. Min Range: -8.0499
Max Act: 8.0499. Min Act: -0.1700
Data Index: 8221408 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.9249. Min Act: -0.1700
Data Index: 8221407 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.8624. Min Act: -0.1700
Data Index: 908463 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.8624. Min Act: -0.1700
Data Index: 1488675 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.8624. Min Act: -0.1700
Data Index: 4644652 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.7999. Min Act: -0.1700
Data Index: 7673548 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.6437. Min Act: -0.1700
Data Index: 6703657 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.5499. Min Act: -0.1700
Data Index: 8261894 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.5187. Min Act: -0.1700
Data Index: 7536497 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.5187. Min Act: -0.1700
Data Index: 6916759 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.4874. Min Act: -0.1700
Data Index: 4644645 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.4249. Min Act: -0.1700
Data Index: 6034166 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.4562. Min Act: -0.1700
Data Index: 637877 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.3937. Min Act: -0.1700
Data Index: 6034169 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.3937. Min Act: -0.1700
Data Index: 4611714 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.3937. Min Act: -0.1700
Data Index: 4633348 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.3624. Min Act: -0.1700
Data Index: 506923 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.3312. Min Act: -0.1700
Data Index: 82676 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.3624. Min Act: -0.1700
Data Index: 6365039 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0499. Min Range: -8.0499
Max Act: 7.3312. Min Act: -0.1700
Data Index: 4967443 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19