Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6037 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0797. Min Range: -7.0797
Max Act: 7.0797. Min Act: -0.1700
Data Index: 503565 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0797. Min Range: -7.0797
Max Act: 7.0797. Min Act: -0.1700
Data Index: 4158029 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0797. Min Range: -7.0797
Max Act: 7.0172. Min Act: -0.1700
Data Index: 7506996 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0797. Min Range: -7.0797
Max Act: 7.0172. Min Act: -0.1700
Data Index: 3914061 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.9547. Min Act: -0.1700
Data Index: 223385 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.9234. Min Act: -0.1700
Data Index: 4851289 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.9234. Min Act: -0.1700
Data Index: 5535099 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.8297. Min Act: -0.1700
Data Index: 3211626 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7672. Min Act: -0.1700
Data Index: 827198 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7672. Min Act: -0.1700
Data Index: 2246516 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7672. Min Act: -0.1700
Data Index: 2212532 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7672. Min Act: -0.1700
Data Index: 1788696 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7672. Min Act: -0.1700
Data Index: 5392941 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7359. Min Act: -0.1700
Data Index: 3820285 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7359. Min Act: -0.1700
Data Index: 1985580 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7047. Min Act: -0.1700
Data Index: 7574117 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7047. Min Act: -0.1700
Data Index: 6626630 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7047. Min Act: -0.1700
Data Index: 5667227 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.6734. Min Act: -0.1700
Data Index: 1029452 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.6734. Min Act: -0.1700
Data Index: 4150944 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19