Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.4599. Min Act: -0.1700
Data Index: 4178244 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.4286. Min Act: -0.1700
Data Index: 6205145 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.4286. Min Act: -0.1700
Data Index: 1545176 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.3349. Min Act: -0.1700
Data Index: 4826849 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.2724. Min Act: -0.1700
Data Index: 7793582 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.2099. Min Act: -0.1700
Data Index: 7612967 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.1474. Min Act: -0.1700
Data Index: 4626136 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.0849. Min Act: -0.1700
Data Index: 8011287 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.0536. Min Act: -0.1700
Data Index: 3905091 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.0224. Min Act: -0.1700
Data Index: 1443464 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4599. Min Range: -7.4599
Max Act: 7.0224. Min Act: -0.1700
Data Index: 4804039 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4599. Min Range: -7.4599
Max Act: 6.9599. Min Act: -0.1700
Data Index: 4841327 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4599. Min Range: -7.4599
Max Act: 6.9599. Min Act: -0.1700
Data Index: 5259244 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4599. Min Range: -7.4599
Max Act: 6.9599. Min Act: -0.1700
Data Index: 6261735 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4599. Min Range: -7.4599
Max Act: 6.9286. Min Act: -0.1700
Data Index: 6081259 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4599. Min Range: -7.4599
Max Act: 6.9286. Min Act: -0.1700
Data Index: 6081262 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4599. Min Range: -7.4599
Max Act: 6.9286. Min Act: -0.1700
Data Index: 3229267 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4599. Min Range: -7.4599
Max Act: 6.8974. Min Act: -0.1700
Data Index: 3803915 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4599. Min Range: -7.4599
Max Act: 6.8974. Min Act: -0.1700
Data Index: 936822 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4599. Min Range: -7.4599
Max Act: 6.8974. Min Act: -0.1700
Data Index: 5003936 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19