Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1001 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.2948. Min Act: -0.1700
Data Index: 7551363 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.2010. Min Act: -0.1700
Data Index: 4948547 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.0448. Min Act: -0.1700
Data Index: 959201 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.0448. Min Act: -0.1700
Data Index: 8584171 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2948. Min Range: -5.2948
Max Act: 5.0135. Min Act: -0.1700
Data Index: 3632432 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.9823. Min Act: -0.1700
Data Index: 2434121 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.9510. Min Act: -0.1700
Data Index: 1225893 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.9198. Min Act: -0.1700
Data Index: 4492528 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8885. Min Act: -0.1700
Data Index: 1460511 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8885. Min Act: -0.1700
Data Index: 1480545 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8885. Min Act: -0.1700
Data Index: 8513497 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8885. Min Act: -0.1700
Data Index: 5326314 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8885. Min Act: -0.1700
Data Index: 6878980 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8573. Min Act: -0.1700
Data Index: 3168100 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8885. Min Act: -0.1700
Data Index: 6103681 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8885. Min Act: -0.1700
Data Index: 1697316 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8573. Min Act: -0.1700
Data Index: 3849115 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8573. Min Act: -0.1700
Data Index: 2238743 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8573. Min Act: -0.1700
Data Index: 1691141 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2948. Min Range: -5.2948
Max Act: 4.8260. Min Act: -0.1700
Data Index: 6487221 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19