Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4237. Min Act: -0.1700
Data Index: 8822838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4237. Min Act: -0.1700
Data Index: 4137576 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4382. Min Act: -0.1700
Data Index: 2801530 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4237. Min Act: -0.1700
Data Index: 4129119 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4382. Min Act: -0.1699
Data Index: 237682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4095. Min Act: -0.1700
Data Index: 2367182 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4095. Min Act: -0.1697
Data Index: 1119467 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4095. Min Act: -0.1673
Data Index: 110243 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4095. Min Act: -0.1695
Data Index: 8168047 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4095. Min Act: -0.1676
Data Index: 152021 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4095. Min Act: -0.1665
Data Index: 3736413 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.3953. Min Act: -0.1596
Data Index: 583712 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4095. Min Act: -0.1700
Data Index: 2586210 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.3953. Min Act: -0.1700
Data Index: 3418143 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.3953. Min Act: -0.1700
Data Index: 4835869 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4095. Min Act: -0.1699
Data Index: 2969150 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.4095. Min Act: -0.1695
Data Index: 1247566 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.3953. Min Act: -0.1683
Data Index: 5452962 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.3813. Min Act: -0.1684
Data Index: 788545 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4382. Min Range: -0.4382
Max Act: 0.3813. Min Act: -0.1676
Data Index: 5216249 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19