Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4666 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.4957. Min Range: -10.4957
Max Act: 10.4957. Min Act: -0.1700
Data Index: 5821748 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4957. Min Range: -10.4957
Max Act: 10.1832. Min Act: -0.1700
Data Index: 2983099 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4957. Min Range: -10.4957
Max Act: 10.0582. Min Act: -0.1700
Data Index: 3346870 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.7457. Min Act: -0.1700
Data Index: 4641029 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.7457. Min Act: -0.1700
Data Index: 8205855 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.7457. Min Act: -0.1700
Data Index: 6163204 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.6832. Min Act: -0.1700
Data Index: 3890245 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.6832. Min Act: -0.1700
Data Index: 847648 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.6832. Min Act: -0.1700
Data Index: 6292265 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.6832. Min Act: -0.1700
Data Index: 42702 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.6207. Min Act: -0.1700
Data Index: 4035888 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.6207. Min Act: -0.1700
Data Index: 7619207 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.5582. Min Act: -0.1700
Data Index: 3324847 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.4332. Min Act: -0.1700
Data Index: 6288685 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.4332. Min Act: -0.1700
Data Index: 8306196 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.3707. Min Act: -0.1700
Data Index: 1816924 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.3707. Min Act: -0.1700
Data Index: 1253978 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.3707. Min Act: -0.1700
Data Index: 2118959 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.3707. Min Act: -0.1700
Data Index: 5476025 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4957. Min Range: -10.4957
Max Act: 9.3707. Min Act: -0.1700
Data Index: 1169485 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19