Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5275 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.3686. Min Act: -0.1700
Data Index: 4372605 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.3686. Min Act: -0.1700
Data Index: 3239339 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.3061. Min Act: -0.1700
Data Index: 6059382 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.2436. Min Act: -0.1700
Data Index: 3112807 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.1811. Min Act: -0.1700
Data Index: 4066106 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.1499. Min Act: -0.1700
Data Index: 2607912 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.1499. Min Act: -0.1700
Data Index: 3277246 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.1186. Min Act: -0.1700
Data Index: 6140253 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.0874. Min Act: -0.1700
Data Index: 5910910 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.0874. Min Act: -0.1700
Data Index: 4357056 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.0561. Min Act: -0.1700
Data Index: 3381720 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.0249. Min Act: -0.1700
Data Index: 3423332 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.0561. Min Act: -0.1700
Data Index: 4508253 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3686. Min Range: -6.3686
Max Act: 6.0249. Min Act: -0.1700
Data Index: 1076952 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3686. Min Range: -6.3686
Max Act: 5.9936. Min Act: -0.1700
Data Index: 2235868 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3686. Min Range: -6.3686
Max Act: 5.9624. Min Act: -0.1700
Data Index: 8784559 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3686. Min Range: -6.3686
Max Act: 5.9624. Min Act: -0.1700
Data Index: 1775513 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3686. Min Range: -6.3686
Max Act: 5.9624. Min Act: -0.1700
Data Index: 3439733 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3686. Min Range: -6.3686
Max Act: 5.9936. Min Act: -0.1700
Data Index: 144066 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3686. Min Range: -6.3686
Max Act: 5.9624. Min Act: -0.1700
Data Index: 4449843 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19