Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3627. Min Range: -6.3627
Max Act: 6.3627. Min Act: -0.1700
Data Index: 5994179 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3627. Min Range: -6.3627
Max Act: 6.2064. Min Act: -0.1700
Data Index: 3725018 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3627. Min Range: -6.3627
Max Act: 6.0189. Min Act: -0.1700
Data Index: 1073972 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3627. Min Range: -6.3627
Max Act: 6.0189. Min Act: -0.1700
Data Index: 6828344 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.9564. Min Act: -0.1700
Data Index: 6209544 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.9564. Min Act: -0.1700
Data Index: 5013008 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8939. Min Act: -0.1700
Data Index: 8273656 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8939. Min Act: -0.1700
Data Index: 1258603 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8939. Min Act: -0.1700
Data Index: 8585620 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8939. Min Act: -0.1700
Data Index: 7098367 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8939. Min Act: -0.1700
Data Index: 4412678 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8314. Min Act: -0.1700
Data Index: 202781 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8627. Min Act: -0.1700
Data Index: 1144267 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8627. Min Act: -0.1700
Data Index: 7589645 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8627. Min Act: -0.1700
Data Index: 972816 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8627. Min Act: -0.1700
Data Index: 2386801 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8314. Min Act: -0.1700
Data Index: 8621257 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8627. Min Act: -0.1700
Data Index: 3632642 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8939. Min Act: -0.1700
Data Index: 5339668 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3627. Min Range: -6.3627
Max Act: 5.8002. Min Act: -0.1700
Data Index: 1396310 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19