Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.8533. Min Act: -0.1700
Data Index: 3365889 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.7595. Min Act: -0.1700
Data Index: 2150290 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.7283. Min Act: -0.1700
Data Index: 8046524 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.6970. Min Act: -0.1700
Data Index: 7264269 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.6970. Min Act: -0.1700
Data Index: 4420483 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.6970. Min Act: -0.1700
Data Index: 1297076 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.6345. Min Act: -0.1700
Data Index: 1294178 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.5720. Min Act: -0.1700
Data Index: 8196042 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.5720. Min Act: -0.1700
Data Index: 452709 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.5408. Min Act: -0.1700
Data Index: 4776565 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.5408. Min Act: -0.1700
Data Index: 7669348 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.5408. Min Act: -0.1700
Data Index: 4986264 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.4783. Min Act: -0.1700
Data Index: 1316243 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.5095. Min Act: -0.1700
Data Index: 8576698 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.5095. Min Act: -0.1700
Data Index: 8044532 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.4783. Min Act: -0.1700
Data Index: 4096697 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.4783. Min Act: -0.1700
Data Index: 3880528 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.5095. Min Act: -0.1700
Data Index: 5695412 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.4783. Min Act: -0.1700
Data Index: 280916 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8533. Min Range: -5.8533
Max Act: 5.4470. Min Act: -0.1700
Data Index: 1339937 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19