Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1480 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1181. Min Range: -5.1181
Max Act: 5.1181. Min Act: -0.1700
Data Index: 268242 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.9931. Min Act: -0.1700
Data Index: 5590733 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.9619. Min Act: -0.1700
Data Index: 1772303 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.9619. Min Act: -0.1700
Data Index: 5420670 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8994. Min Act: -0.1700
Data Index: 5320164 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8994. Min Act: -0.1700
Data Index: 877206 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8681. Min Act: -0.1700
Data Index: 5760173 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8994. Min Act: -0.1700
Data Index: 5758892 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8681. Min Act: -0.1700
Data Index: 1835716 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8681. Min Act: -0.1700
Data Index: 4784128 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8994. Min Act: -0.1700
Data Index: 5890439 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8369. Min Act: -0.1700
Data Index: 7114798 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8369. Min Act: -0.1700
Data Index: 58015 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8369. Min Act: -0.1700
Data Index: 6977954 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.7744. Min Act: -0.1700
Data Index: 3836357 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8056. Min Act: -0.1700
Data Index: 5329703 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8056. Min Act: -0.1700
Data Index: 5112545 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8369. Min Act: -0.1700
Data Index: 7779282 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.7744. Min Act: -0.1700
Data Index: 2910586 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1181. Min Range: -5.1181
Max Act: 4.8056. Min Act: -0.1700
Data Index: 2048150 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19