Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1400 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.4693. Min Act: -0.1700
Data Index: 1114272 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.4068. Min Act: -0.1700
Data Index: 6601952 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2817. Min Act: -0.1700
Data Index: 2019400 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2505. Min Act: -0.1700
Data Index: 7692127 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2817. Min Act: -0.1700
Data Index: 4870261 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.3130. Min Act: -0.1700
Data Index: 3101426 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2505. Min Act: -0.1700
Data Index: 1589429 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2192. Min Act: -0.1700
Data Index: 4279953 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2192. Min Act: -0.1700
Data Index: 7607277 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2192. Min Act: -0.1700
Data Index: 5544576 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2192. Min Act: -0.1700
Data Index: 4422036 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2192. Min Act: -0.1700
Data Index: 5201999 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.2192. Min Act: -0.1700
Data Index: 7391118 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.1880. Min Act: -0.1700
Data Index: 1470301 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.1255. Min Act: -0.1700
Data Index: 6185881 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.1567. Min Act: -0.1700
Data Index: 3214512 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.1567. Min Act: -0.1700
Data Index: 608858 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.1567. Min Act: -0.1700
Data Index: 4944666 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.1567. Min Act: -0.1700
Data Index: 3738922 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4693. Min Range: -4.4693
Max Act: 4.1255. Min Act: -0.1700
Data Index: 2015017 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19