Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2302 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0549. Min Range: -5.0549
Max Act: 5.0549. Min Act: -0.1700
Data Index: 27147 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0549. Min Range: -5.0549
Max Act: 5.0237. Min Act: -0.1700
Data Index: 4425229 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.9612. Min Act: -0.1700
Data Index: 281883 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.8987. Min Act: -0.1700
Data Index: 5200894 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.8049. Min Act: -0.1700
Data Index: 5324766 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.8362. Min Act: -0.1700
Data Index: 2535458 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.7737. Min Act: -0.1700
Data Index: 916580 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.7737. Min Act: -0.1700
Data Index: 5796767 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.7424. Min Act: -0.1700
Data Index: 4514701 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.7424. Min Act: -0.1700
Data Index: 858067 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.7424. Min Act: -0.1700
Data Index: 6294666 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.7424. Min Act: -0.1700
Data Index: 4337811 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.6799. Min Act: -0.1700
Data Index: 6789998 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.6174. Min Act: -0.1700
Data Index: 5687310 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.6487. Min Act: -0.1700
Data Index: 7451593 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.6487. Min Act: -0.1700
Data Index: 3729090 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.6487. Min Act: -0.1700
Data Index: 4940543 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.6174. Min Act: -0.1700
Data Index: 4155893 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.6174. Min Act: -0.1700
Data Index: 2665786 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0549. Min Range: -5.0549
Max Act: 4.6174. Min Act: -0.1700
Data Index: 2824488 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19