Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1993. Min Range: -5.1993
Max Act: 5.1993. Min Act: -0.1700
Data Index: 8394303 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1993. Min Range: -5.1993
Max Act: 5.0743. Min Act: -0.1700
Data Index: 8691284 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1993. Min Range: -5.1993
Max Act: 5.0743. Min Act: -0.1700
Data Index: 6738080 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.8556. Min Act: -0.1700
Data Index: 6590848 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.8556. Min Act: -0.1700
Data Index: 1800108 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.8243. Min Act: -0.1700
Data Index: 7164430 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.8243. Min Act: -0.1700
Data Index: 5247854 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.8243. Min Act: -0.1700
Data Index: 4229220 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.8243. Min Act: -0.1700
Data Index: 3122747 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7931. Min Act: -0.1700
Data Index: 328440 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.8243. Min Act: -0.1700
Data Index: 2026851 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7618. Min Act: -0.1700
Data Index: 8291373 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7618. Min Act: -0.1700
Data Index: 644033 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7618. Min Act: -0.1700
Data Index: 5868582 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7306. Min Act: -0.1700
Data Index: 6439110 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7618. Min Act: -0.1700
Data Index: 3235186 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7931. Min Act: -0.1700
Data Index: 3181741 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7618. Min Act: -0.1700
Data Index: 902236 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7618. Min Act: -0.1700
Data Index: 4534002 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1993. Min Range: -5.1993
Max Act: 4.7306. Min Act: -0.1700
Data Index: 4140535 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19