Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3022 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.7791. Min Act: -0.1700
Data Index: 4327846 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.4666. Min Act: -0.1700
Data Index: 1628190 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.4041. Min Act: -0.1700
Data Index: 4040202 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.3416. Min Act: -0.1700
Data Index: 2790977 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.3416. Min Act: -0.1700
Data Index: 7243308 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.3416. Min Act: -0.1700
Data Index: 2702855 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.2791. Min Act: -0.1700
Data Index: 2702851 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.2791. Min Act: -0.1700
Data Index: 7635425 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.2791. Min Act: -0.1700
Data Index: 2318034 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.2166. Min Act: -0.1700
Data Index: 3864220 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.2166. Min Act: -0.1700
Data Index: 7589745 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.1541. Min Act: -0.1700
Data Index: 3450116 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.0916. Min Act: -0.1700
Data Index: 7098213 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.0916. Min Act: -0.1700
Data Index: 2047727 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.1541. Min Act: -0.1700
Data Index: 3055205 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.1541. Min Act: -0.1700
Data Index: 2287731 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.0916. Min Act: -0.1700
Data Index: 1320073 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.0291. Min Act: -0.1700
Data Index: 5195106 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.0291. Min Act: -0.1700
Data Index: 432920 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7791. Min Range: -8.7791
Max Act: 8.0291. Min Act: -0.1700
Data Index: 4918970 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19