Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4914 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.3602. Min Act: -0.1700
Data Index: 7048805 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.3289. Min Act: -0.1700
Data Index: 7183626 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2352. Min Act: -0.1700
Data Index: 8378641 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2664. Min Act: -0.1700
Data Index: 8461515 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2977. Min Act: -0.1700
Data Index: 4012241 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2664. Min Act: -0.1700
Data Index: 8724440 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2664. Min Act: -0.1700
Data Index: 5987185 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2352. Min Act: -0.1700
Data Index: 6275769 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2352. Min Act: -0.1700
Data Index: 6299269 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2352. Min Act: -0.1700
Data Index: 4211214 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2352. Min Act: -0.1700
Data Index: 6050998 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2352. Min Act: -0.1700
Data Index: 2230520 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2352. Min Act: -0.1700
Data Index: 958950 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2352. Min Act: -0.1700
Data Index: 7747892 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2352. Min Act: -0.1700
Data Index: 7961259 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2039. Min Act: -0.1700
Data Index: 3137345 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2039. Min Act: -0.1700
Data Index: 1126378 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2039. Min Act: -0.1700
Data Index: 7559565 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2039. Min Act: -0.1700
Data Index: 1829918 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3602. Min Range: -5.3602
Max Act: 5.2039. Min Act: -0.1700
Data Index: 2400210 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19