Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2433 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.5428. Min Act: -0.1700
Data Index: 3054247 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.5590. Min Act: -0.1700
Data Index: 4528111 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.5428. Min Act: -0.1700
Data Index: 5054008 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.5267. Min Act: -0.1700
Data Index: 7161595 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.5105. Min Act: -0.1700
Data Index: 4083819 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.5105. Min Act: -0.1700
Data Index: 5728988 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4943. Min Act: -0.1700
Data Index: 5752498 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4943. Min Act: -0.1700
Data Index: 3424426 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4943. Min Act: -0.1700
Data Index: 6809655 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4943. Min Act: -0.1700
Data Index: 5692289 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4781. Min Act: -0.1700
Data Index: 5777173 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4781. Min Act: -0.1700
Data Index: 270761 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4618. Min Act: -0.1700
Data Index: 4668873 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4456. Min Act: -0.1700
Data Index: 2371059 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4456. Min Act: -0.1700
Data Index: 8003467 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4618. Min Act: -0.1700
Data Index: 7068671 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4618. Min Act: -0.1700
Data Index: 4232798 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4618. Min Act: -0.1700
Data Index: 7741745 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4456. Min Act: -0.1700
Data Index: 4621474 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5590. Min Range: -2.5590
Max Act: 2.4456. Min Act: -0.1700
Data Index: 6506446 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19