Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0193. Min Range: -8.0193
Max Act: 8.0193. Min Act: -0.1700
Data Index: 6288840 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0193. Min Range: -8.0193
Max Act: 8.0193. Min Act: -0.1700
Data Index: 173373 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.8318. Min Act: -0.1700
Data Index: 4039936 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.8943. Min Act: -0.1700
Data Index: 3637214 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.8318. Min Act: -0.1700
Data Index: 4255754 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.7693. Min Act: -0.1700
Data Index: 691027 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.8318. Min Act: -0.1700
Data Index: 8070570 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.7693. Min Act: -0.1700
Data Index: 6579062 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.8318. Min Act: -0.1700
Data Index: 8451498 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.7693. Min Act: -0.1700
Data Index: 7306407 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.7693. Min Act: -0.1700
Data Index: 6039355 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.7068. Min Act: -0.1700
Data Index: 8298414 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.7693. Min Act: -0.1700
Data Index: 4121704 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.6443. Min Act: -0.1700
Data Index: 2588151 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.7068. Min Act: -0.1700
Data Index: 2769650 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.7068. Min Act: -0.1700
Data Index: 6408983 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.6443. Min Act: -0.1700
Data Index: 7201312 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.6443. Min Act: -0.1700
Data Index: 4784856 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.5818. Min Act: -0.1700
Data Index: 5526359 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0193. Min Range: -8.0193
Max Act: 7.6443. Min Act: -0.1700
Data Index: 1953658 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19