Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1082 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.7651. Min Act: -0.1700
Data Index: 2467719 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.6713. Min Act: -0.1700
Data Index: 8080662 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.6401. Min Act: -0.1700
Data Index: 4075502 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.6401. Min Act: -0.1700
Data Index: 199555 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.6401. Min Act: -0.1700
Data Index: 5226353 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.5776. Min Act: -0.1700
Data Index: 3616878 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.5463. Min Act: -0.1700
Data Index: 4982283 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.5463. Min Act: -0.1700
Data Index: 2593235 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.5151. Min Act: -0.1700
Data Index: 8513557 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.4838. Min Act: -0.1700
Data Index: 6259321 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.5151. Min Act: -0.1700
Data Index: 6707552 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.4526. Min Act: -0.1700
Data Index: 5977650 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.4838. Min Act: -0.1700
Data Index: 2685718 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.4526. Min Act: -0.1700
Data Index: 4678591 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.4213. Min Act: -0.1700
Data Index: 1841110 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.4213. Min Act: -0.1700
Data Index: 7722814 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.4213. Min Act: -0.1700
Data Index: 6370247 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.3901. Min Act: -0.1700
Data Index: 1554362 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.3588. Min Act: -0.1700
Data Index: 2598169 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7651. Min Range: -6.7651
Max Act: 6.3901. Min Act: -0.1700
Data Index: 88632 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19