Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.2553. Min Act: -0.1700
Data Index: 2348695 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.2239. Min Act: -0.1700
Data Index: 6727706 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.2396. Min Act: -0.1700
Data Index: 1344383 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.1610. Min Act: -0.1700
Data Index: 4288748 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.1137. Min Act: -0.1700
Data Index: 750852 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.1137. Min Act: -0.1700
Data Index: 2981536 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0980. Min Act: -0.1700
Data Index: 6188948 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0980. Min Act: -0.1700
Data Index: 5308147 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0664. Min Act: -0.1700
Data Index: 7021775 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0822. Min Act: -0.1700
Data Index: 5226796 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0664. Min Act: -0.1700
Data Index: 1886725 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0664. Min Act: -0.1700
Data Index: 7676196 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0664. Min Act: -0.1700
Data Index: 6937094 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0507. Min Act: -0.1700
Data Index: 7925220 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0507. Min Act: -0.1700
Data Index: 7741519 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0349. Min Act: -0.1700
Data Index: 7574771 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0349. Min Act: -0.1700
Data Index: 5366675 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0191. Min Act: -0.1700
Data Index: 8404812 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2553. Min Range: -3.2553
Max Act: 3.0191. Min Act: -0.1700
Data Index: 7273419 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2553. Min Range: -3.2553
Max Act: 2.9875. Min Act: -0.1700
Data Index: 7012485 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19