Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.5359. Min Act: -0.1700
Data Index: 1182704 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4109. Min Range: -7.4109
Max Act: 7.4109. Min Act: -0.1699
Data Index: 3484330 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.4422. Min Act: -0.1700
Data Index: 8634036 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.1609. Min Act: -0.1700
Data Index: 2823105 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.1609. Min Act: -0.1700
Data Index: 907261 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4109. Min Range: -7.4109
Max Act: 6.2859. Min Act: -0.1700
Data Index: 2123709 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.2547. Min Act: -0.1700
Data Index: 8222233 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4109. Min Range: -7.4109
Max Act: 4.8484. Min Act: -0.1700
Data Index: 6312822 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.9734. Min Act: -0.1700
Data Index: 2703890 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.9422. Min Act: -0.1700
Data Index: 8581270 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.2234. Min Act: -0.1700
Data Index: 4515270 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.5359. Min Act: -0.1700
Data Index: 2655282 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.7234. Min Act: -0.1700
Data Index: 2454379 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.8797. Min Act: -0.1700
Data Index: 6750273 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4109. Min Range: -7.4109
Max Act: 4.9109. Min Act: -0.1700
Data Index: 4175113 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.7859. Min Act: -0.1700
Data Index: 7626011 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.2234. Min Act: -0.1700
Data Index: 4857208 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.2859. Min Act: -0.1700
Data Index: 6630317 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.7547. Min Act: -0.1700
Data Index: 646557 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4109. Min Range: -7.4109
Max Act: 5.6922. Min Act: -0.1700
Data Index: 443954 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19