Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 411 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.9786. Min Act: -0.1700
Data Index: 8520846 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.9161. Min Act: -0.1700
Data Index: 3607131 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.8849. Min Act: -0.1700
Data Index: 62969 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.8536. Min Act: -0.1700
Data Index: 8049565 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.7911. Min Act: -0.1700
Data Index: 7764345 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.7911. Min Act: -0.1700
Data Index: 1753610 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.7599. Min Act: -0.1700
Data Index: 4888518 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.7911. Min Act: -0.1700
Data Index: 6379706 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.7599. Min Act: -0.1700
Data Index: 3748656 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.7286. Min Act: -0.1700
Data Index: 2174523 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6974. Min Act: -0.1700
Data Index: 4437053 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6974. Min Act: -0.1700
Data Index: 5113465 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6974. Min Act: -0.1700
Data Index: 8651980 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6661. Min Act: -0.1700
Data Index: 8042568 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6661. Min Act: -0.1700
Data Index: 3333321 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6661. Min Act: -0.1700
Data Index: 2211240 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6036. Min Act: -0.1700
Data Index: 7845124 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6661. Min Act: -0.1700
Data Index: 6641909 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6349. Min Act: -0.1700
Data Index: 2151529 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9786. Min Range: -6.9786
Max Act: 6.6349. Min Act: -0.1700
Data Index: 6866483 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19