Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.5011. Min Act: -0.1700
Data Index: 3444572 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.3136. Min Act: -0.1700
Data Index: 1445249 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.2824. Min Act: -0.1700
Data Index: 6922440 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.2824. Min Act: -0.1700
Data Index: 3163179 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.2511. Min Act: -0.1700
Data Index: 4447062 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.2511. Min Act: -0.1700
Data Index: 1094118 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.2511. Min Act: -0.1700
Data Index: 5444308 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.2199. Min Act: -0.1700
Data Index: 2393916 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.1886. Min Act: -0.1700
Data Index: 5436680 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.1886. Min Act: -0.1700
Data Index: 1393176 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.1886. Min Act: -0.1700
Data Index: 1091040 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.1574. Min Act: -0.1700
Data Index: 8604898 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.1574. Min Act: -0.1700
Data Index: 4562850 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.1261. Min Act: -0.1700
Data Index: 5990470 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.1261. Min Act: -0.1700
Data Index: 218078 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.1261. Min Act: -0.1700
Data Index: 3856218 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.0636. Min Act: -0.1700
Data Index: 6823027 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.0949. Min Act: -0.1700
Data Index: 2604916 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.0636. Min Act: -0.1700
Data Index: 3600529 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5011. Min Range: -6.5011
Max Act: 6.0636. Min Act: -0.1700
Data Index: 7325393 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19