Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1998 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.7010. Min Act: -0.1700
Data Index: 83230 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.6228. Min Act: -0.1700
Data Index: 7735452 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.6071. Min Act: -0.1700
Data Index: 442766 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.5915. Min Act: -0.1700
Data Index: 8698598 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.5445. Min Act: -0.1700
Data Index: 3693647 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.5288. Min Act: -0.1700
Data Index: 1066692 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.5132. Min Act: -0.1700
Data Index: 644520 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4975. Min Act: -0.1700
Data Index: 1102585 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.5288. Min Act: -0.1700
Data Index: 4244798 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4819. Min Act: -0.1700
Data Index: 7332561 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4819. Min Act: -0.1700
Data Index: 5599820 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4819. Min Act: -0.1700
Data Index: 4330354 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4662. Min Act: -0.1700
Data Index: 8147914 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4505. Min Act: -0.1700
Data Index: 3130447 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4349. Min Act: -0.1700
Data Index: 80508 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4505. Min Act: -0.1700
Data Index: 8710102 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4349. Min Act: -0.1700
Data Index: 8029329 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4505. Min Act: -0.1700
Data Index: 5003961 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4505. Min Act: -0.1700
Data Index: 4649434 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7010. Min Range: -3.7010
Max Act: 3.4349. Min Act: -0.1700
Data Index: 5636030 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19