Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.7297. Min Act: -0.1700
Data Index: 6280144 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.6360. Min Act: -0.1700
Data Index: 3124661 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.6360. Min Act: -0.1700
Data Index: 5708257 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.5110. Min Act: -0.1700
Data Index: 1289586 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.4797. Min Act: -0.1700
Data Index: 6694461 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.4485. Min Act: -0.1700
Data Index: 7290974 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.3860. Min Act: -0.1700
Data Index: 1606218 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.3860. Min Act: -0.1700
Data Index: 2923885 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.3860. Min Act: -0.1700
Data Index: 6823179 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.3860. Min Act: -0.1700
Data Index: 6185748 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.3547. Min Act: -0.1700
Data Index: 5830135 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.3547. Min Act: -0.1700
Data Index: 276996 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.2922. Min Act: -0.1700
Data Index: 6185749 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.3235. Min Act: -0.1700
Data Index: 2831148 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.2922. Min Act: -0.1700
Data Index: 8377788 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.2922. Min Act: -0.1700
Data Index: 5767221 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.2610. Min Act: -0.1700
Data Index: 5898412 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.2297. Min Act: -0.1700
Data Index: 5736628 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.1985. Min Act: -0.1700
Data Index: 3537997 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7297. Min Range: -5.7297
Max Act: 5.1985. Min Act: -0.1700
Data Index: 2197429 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19