Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2345 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2445. Min Range: -8.2445
Max Act: 8.2445. Min Act: -0.1700
Data Index: 3645179 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2445. Min Range: -8.2445
Max Act: 8.2445. Min Act: -0.1700
Data Index: 3672245 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2445. Min Range: -8.2445
Max Act: 8.0570. Min Act: -0.1700
Data Index: 3672246 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.9945. Min Act: -0.1700
Data Index: 6106700 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.9320. Min Act: -0.1700
Data Index: 6472841 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.9320. Min Act: -0.1700
Data Index: 4218885 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.9320. Min Act: -0.1700
Data Index: 61338 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.8695. Min Act: -0.1700
Data Index: 3502762 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.8070. Min Act: -0.1700
Data Index: 472109 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.8070. Min Act: -0.1700
Data Index: 2764168 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.7445. Min Act: -0.1700
Data Index: 3170201 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.7445. Min Act: -0.1700
Data Index: 7814653 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.7445. Min Act: -0.1700
Data Index: 8262474 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.7445. Min Act: -0.1700
Data Index: 4371132 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.7445. Min Act: -0.1700
Data Index: 8733049 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.6820. Min Act: -0.1700
Data Index: 5406424 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.6195. Min Act: -0.1700
Data Index: 3478900 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.6820. Min Act: -0.1700
Data Index: 6425745 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.5882. Min Act: -0.1700
Data Index: 154123 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2445. Min Range: -8.2445
Max Act: 7.5882. Min Act: -0.1700
Data Index: 100621 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19