Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4361 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.4996. Min Act: -0.1700
Data Index: 1246141 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.4371. Min Act: -0.1700
Data Index: 1099558 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.4371. Min Act: -0.1700
Data Index: 2605794 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.4059. Min Act: -0.1700
Data Index: 7570926 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3746. Min Act: -0.1700
Data Index: 2061117 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3746. Min Act: -0.1700
Data Index: 6397576 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3746. Min Act: -0.1700
Data Index: 3840753 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3434. Min Act: -0.1700
Data Index: 3981442 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3434. Min Act: -0.1700
Data Index: 6947951 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3121. Min Act: -0.1700
Data Index: 7657887 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3121. Min Act: -0.1700
Data Index: 8633554 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3121. Min Act: -0.1700
Data Index: 8706741 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2809. Min Act: -0.1700
Data Index: 2085616 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2809. Min Act: -0.1700
Data Index: 2885036 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2496. Min Act: -0.1700
Data Index: 3061423 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2496. Min Act: -0.1700
Data Index: 905499 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2496. Min Act: -0.1700
Data Index: 196859 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2184. Min Act: -0.1700
Data Index: 1368059 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.1871. Min Act: -0.1700
Data Index: 3379070 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.1871. Min Act: -0.1700
Data Index: 2698100 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19