Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 5145004 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 5973312 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 6016547 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 6149801 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 6220430 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 7056323 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 7898407 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 3874693 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2962. Min Act: -0.1700
Data Index: 1977387 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 105478 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 2589582 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 2102960 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 911851 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 907204 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 2030820 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 1991645 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 1738272 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 1683381 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2650. Min Act: -0.1700
Data Index: 1574738 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2962. Min Range: -4.2962
Max Act: 4.2337. Min Act: -0.1700
Data Index: 1519789 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19