Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4094 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0983. Min Range: -9.0983
Max Act: 9.0983. Min Act: -0.1700
Data Index: 1043017 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.9733. Min Act: -0.1700
Data Index: 545461 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.8483. Min Act: -0.1700
Data Index: 6542380 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.5983. Min Act: -0.1700
Data Index: 6612057 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.5983. Min Act: -0.1700
Data Index: 116374 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.5983. Min Act: -0.1700
Data Index: 1059163 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.5358. Min Act: -0.1700
Data Index: 8456607 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.4733. Min Act: -0.1700
Data Index: 2033690 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.4108. Min Act: -0.1700
Data Index: 6871249 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.4108. Min Act: -0.1700
Data Index: 7167703 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.4108. Min Act: -0.1700
Data Index: 5702145 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.3483. Min Act: -0.1700
Data Index: 8143329 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.3483. Min Act: -0.1700
Data Index: 7544788 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.3483. Min Act: -0.1700
Data Index: 1726369 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.3483. Min Act: -0.1700
Data Index: 8401613 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.4108. Min Act: -0.1700
Data Index: 3206479 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.2858. Min Act: -0.1700
Data Index: 3995665 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.2858. Min Act: -0.1700
Data Index: 779052 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.2858. Min Act: -0.1700
Data Index: 5356597 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0983. Min Range: -9.0983
Max Act: 8.2858. Min Act: -0.1700
Data Index: 8156895 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19