Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0658. Min Range: -7.0658
Max Act: 7.0658. Min Act: -0.1700
Data Index: 2877599 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0658. Min Range: -7.0658
Max Act: 7.0033. Min Act: -0.1700
Data Index: 2644927 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.8783. Min Act: -0.1700
Data Index: 3836788 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.8158. Min Act: -0.1700
Data Index: 3477595 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.7845. Min Act: -0.1700
Data Index: 3343973 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.7533. Min Act: -0.1700
Data Index: 5577542 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.7533. Min Act: -0.1700
Data Index: 6164359 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.6595. Min Act: -0.1700
Data Index: 5240314 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.6908. Min Act: -0.1700
Data Index: 6878819 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.6283. Min Act: -0.1700
Data Index: 6082654 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.6283. Min Act: -0.1700
Data Index: 5413556 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.5970. Min Act: -0.1700
Data Index: 7997186 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.5970. Min Act: -0.1700
Data Index: 5519901 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.5970. Min Act: -0.1700
Data Index: 7458945 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.5658. Min Act: -0.1700
Data Index: 462965 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.5345. Min Act: -0.1700
Data Index: 7195221 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.5345. Min Act: -0.1700
Data Index: 3443705 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.5345. Min Act: -0.1700
Data Index: 2591191 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.5033. Min Act: -0.1700
Data Index: 1655871 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0658. Min Range: -7.0658
Max Act: 6.5345. Min Act: -0.1700
Data Index: 4770080 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19