Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2145 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.6103. Min Act: -0.1700
Data Index: 2405577 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.3603. Min Act: -0.1700
Data Index: 6983731 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.2353. Min Act: -0.1700
Data Index: 3847367 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.1728. Min Act: -0.1700
Data Index: 5053550 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.2041. Min Act: -0.1700
Data Index: 7895862 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.1416. Min Act: -0.1700
Data Index: 6332325 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.0791. Min Act: -0.1700
Data Index: 3556744 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.0791. Min Act: -0.1700
Data Index: 5646126 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.0478. Min Act: -0.1700
Data Index: 5151962 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6103. Min Range: -7.6103
Max Act: 7.0166. Min Act: -0.1700
Data Index: 5953738 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.9853. Min Act: -0.1700
Data Index: 6701622 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.9541. Min Act: -0.1700
Data Index: 3094158 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.9541. Min Act: -0.1700
Data Index: 3940733 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.9541. Min Act: -0.1700
Data Index: 2883492 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.9541. Min Act: -0.1700
Data Index: 5667205 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.9541. Min Act: -0.1700
Data Index: 101179 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.9541. Min Act: -0.1700
Data Index: 8530296 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.9541. Min Act: -0.1700
Data Index: 5476975 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.9541. Min Act: -0.1700
Data Index: 4144977 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6103. Min Range: -7.6103
Max Act: 6.8916. Min Act: -0.1700
Data Index: 4148177 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19