Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 475 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3588. Min Range: -5.3588
Max Act: 5.3588. Min Act: -0.1700
Data Index: 8178319 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3588. Min Range: -5.3588
Max Act: 5.2963. Min Act: -0.1700
Data Index: 2906372 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3588. Min Range: -5.3588
Max Act: 5.2651. Min Act: -0.1700
Data Index: 2597308 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3588. Min Range: -5.3588
Max Act: 5.2026. Min Act: -0.1700
Data Index: 4089978 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3588. Min Range: -5.3588
Max Act: 5.1713. Min Act: -0.1700
Data Index: 1094076 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3588. Min Range: -5.3588
Max Act: 5.1088. Min Act: -0.1700
Data Index: 800043 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3588. Min Range: -5.3588
Max Act: 5.0151. Min Act: -0.1700
Data Index: 7560339 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.9838. Min Act: -0.1700
Data Index: 8497130 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.9838. Min Act: -0.1700
Data Index: 6855900 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.9526. Min Act: -0.1700
Data Index: 7241807 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.9526. Min Act: -0.1700
Data Index: 7253318 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.8901. Min Act: -0.1700
Data Index: 4927084 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.9213. Min Act: -0.1700
Data Index: 8601542 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.8901. Min Act: -0.1700
Data Index: 6419984 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.9213. Min Act: -0.1700
Data Index: 2491324 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.8901. Min Act: -0.1700
Data Index: 836960 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.8588. Min Act: -0.1700
Data Index: 5067888 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.8276. Min Act: -0.1700
Data Index: 8143791 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.8276. Min Act: -0.1700
Data Index: 1133950 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3588. Min Range: -5.3588
Max Act: 4.7963. Min Act: -0.1700
Data Index: 4347422 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19