Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.5656. Min Act: -0.1700
Data Index: 437188 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.5343. Min Act: -0.1700
Data Index: 7636706 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.5031. Min Act: -0.1700
Data Index: 1874138 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.4718. Min Act: -0.1700
Data Index: 4830320 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.4406. Min Act: -0.1700
Data Index: 4514018 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.4406. Min Act: -0.1700
Data Index: 8297831 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.4093. Min Act: -0.1700
Data Index: 4332400 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3781. Min Act: -0.1700
Data Index: 6823743 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3468. Min Act: -0.1700
Data Index: 8280088 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3468. Min Act: -0.1700
Data Index: 4894034 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3468. Min Act: -0.1700
Data Index: 4270410 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3468. Min Act: -0.1700
Data Index: 5904641 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3468. Min Act: -0.1700
Data Index: 209089 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3468. Min Act: -0.1700
Data Index: 5013282 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3468. Min Act: -0.1700
Data Index: 856098 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3156. Min Act: -0.1700
Data Index: 3362616 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.2843. Min Act: -0.1700
Data Index: 1698247 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3156. Min Act: -0.1700
Data Index: 7796501 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.2843. Min Act: -0.1700
Data Index: 8230881 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5656. Min Range: -4.5656
Max Act: 4.3156. Min Act: -0.1700
Data Index: 1737889 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19