Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0277. Min Range: -5.0277
Max Act: 5.0277. Min Act: -0.1700
Data Index: 5486715 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0277. Min Range: -5.0277
Max Act: 5.0277. Min Act: -0.1700
Data Index: 8502988 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9965. Min Act: -0.1700
Data Index: 1243475 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9652. Min Act: -0.1700
Data Index: 1682771 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9652. Min Act: -0.1700
Data Index: 1171649 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9965. Min Act: -0.1700
Data Index: 7528303 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9027. Min Act: -0.1700
Data Index: 636627 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9340. Min Act: -0.1700
Data Index: 5008801 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9652. Min Act: -0.1700
Data Index: 3583593 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9340. Min Act: -0.1700
Data Index: 2961303 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9340. Min Act: -0.1700
Data Index: 3698262 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9340. Min Act: -0.1700
Data Index: 3677224 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9027. Min Act: -0.1700
Data Index: 6227758 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9027. Min Act: -0.1700
Data Index: 5707083 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9027. Min Act: -0.1700
Data Index: 1515279 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9027. Min Act: -0.1700
Data Index: 8370648 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9027. Min Act: -0.1700
Data Index: 3998101 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.9027. Min Act: -0.1700
Data Index: 6336840 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.8715. Min Act: -0.1700
Data Index: 5915886 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0277. Min Range: -5.0277
Max Act: 4.8715. Min Act: -0.1700
Data Index: 1061713 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19