Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 945 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1183. Min Range: -4.1183
Max Act: 4.1183. Min Act: -0.1700
Data Index: 4058003 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1183. Min Range: -4.1183
Max Act: 4.1183. Min Act: -0.1700
Data Index: 5117768 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1183. Min Range: -4.1183
Max Act: 4.0870. Min Act: -0.1700
Data Index: 6069561 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.9933. Min Act: -0.1700
Data Index: 3040217 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.9620. Min Act: -0.1700
Data Index: 4585512 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.9620. Min Act: -0.1700
Data Index: 2071864 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.9933. Min Act: -0.1700
Data Index: 8623356 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.9151. Min Act: -0.1700
Data Index: 3762593 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.9307. Min Act: -0.1700
Data Index: 2170942 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.9151. Min Act: -0.1700
Data Index: 3984537 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8526. Min Act: -0.1700
Data Index: 3512974 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8526. Min Act: -0.1700
Data Index: 2931393 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8213. Min Act: -0.1700
Data Index: 6762449 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8213. Min Act: -0.1700
Data Index: 1230794 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8369. Min Act: -0.1700
Data Index: 1489198 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8213. Min Act: -0.1700
Data Index: 6218736 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8057. Min Act: -0.1700
Data Index: 7139787 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8213. Min Act: -0.1700
Data Index: 8396743 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8369. Min Act: -0.1700
Data Index: 2437701 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1183. Min Range: -4.1183
Max Act: 3.8213. Min Act: -0.1700
Data Index: 5285627 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19