Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1070 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.4537. Min Act: -0.1700
Data Index: 3748799 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.3599. Min Act: -0.1700
Data Index: 4041740 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.2349. Min Act: -0.1700
Data Index: 2136925 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.2662. Min Act: -0.1700
Data Index: 574785 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.2037. Min Act: -0.1700
Data Index: 8513028 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.2349. Min Act: -0.1700
Data Index: 7183792 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.1724. Min Act: -0.1700
Data Index: 7270178 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.2037. Min Act: -0.1700
Data Index: 7135456 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.1724. Min Act: -0.1700
Data Index: 667405 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.1411. Min Act: -0.1700
Data Index: 4057239 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.1411. Min Act: -0.1700
Data Index: 4796766 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.1099. Min Act: -0.1700
Data Index: 3205185 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.0786. Min Act: -0.1700
Data Index: 8508542 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.0786. Min Act: -0.1700
Data Index: 1216266 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.0786. Min Act: -0.1700
Data Index: 4183587 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.0786. Min Act: -0.1700
Data Index: 8500321 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.0474. Min Act: -0.1700
Data Index: 8198791 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.0161. Min Act: -0.1700
Data Index: 4663518 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.0474. Min Act: -0.1700
Data Index: 7267311 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4537. Min Range: -4.4537
Max Act: 4.0474. Min Act: -0.1700
Data Index: 1224632 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19