Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.5928. Min Act: -0.1700
Data Index: 8115218 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.6084. Min Act: -0.1700
Data Index: 295111 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.5771. Min Act: -0.1700
Data Index: 977976 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.5458. Min Act: -0.1700
Data Index: 5437897 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.4518. Min Act: -0.1700
Data Index: 7053031 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.4362. Min Act: -0.1700
Data Index: 6513972 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.4362. Min Act: -0.1700
Data Index: 4060950 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.4205. Min Act: -0.1700
Data Index: 5544253 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.3891. Min Act: -0.1700
Data Index: 1870004 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.4048. Min Act: -0.1700
Data Index: 67133 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.4205. Min Act: -0.1700
Data Index: 572765 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.4048. Min Act: -0.1700
Data Index: 977977 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.4048. Min Act: -0.1700
Data Index: 505090 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.4048. Min Act: -0.1700
Data Index: 1031329 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.3735. Min Act: -0.1700
Data Index: 2492332 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.3891. Min Act: -0.1700
Data Index: 2107528 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.3891. Min Act: -0.1700
Data Index: 7059561 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.3578. Min Act: -0.1700
Data Index: 373781 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.3421. Min Act: -0.1700
Data Index: 6182901 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6084. Min Range: -3.6084
Max Act: 3.3891. Min Act: -0.1700
Data Index: 5411771 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19