Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.5912. Min Act: -0.1700
Data Index: 5852471 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.4943. Min Act: -0.1700
Data Index: 2783323 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.4618. Min Act: -0.1695
Data Index: 5991228 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.4455. Min Act: -0.1700
Data Index: 291103 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.4455. Min Act: -0.1700
Data Index: 7558193 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.4455. Min Act: -0.1700
Data Index: 3133116 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.4293. Min Act: -0.1700
Data Index: 347457 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3967. Min Act: -0.1700
Data Index: 6983796 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.4130. Min Act: -0.1700
Data Index: 4246866 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3803. Min Act: -0.1700
Data Index: 4561706 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3967. Min Act: -0.1700
Data Index: 2494739 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3967. Min Act: -0.1698
Data Index: 1582097 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3803. Min Act: -0.1700
Data Index: 3783856 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3640. Min Act: -0.1700
Data Index: 6983795 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3640. Min Act: -0.1700
Data Index: 8095966 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3803. Min Act: -0.1700
Data Index: 3328334 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3803. Min Act: -0.1700
Data Index: 5061156 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3476. Min Act: -0.1700
Data Index: 5737895 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3476. Min Act: -0.1700
Data Index: 4858734 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5912. Min Range: -2.5912
Max Act: 2.3640. Min Act: -0.1700
Data Index: 7841313 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19