Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3192. Min Range: -7.3192
Max Act: 7.3192. Min Act: -0.1700
Data Index: 8460459 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3192. Min Range: -7.3192
Max Act: 7.1630. Min Act: -0.1700
Data Index: 8080939 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3192. Min Range: -7.3192
Max Act: 7.0067. Min Act: -0.1700
Data Index: 4158189 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.8505. Min Act: -0.1700
Data Index: 8307377 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.8192. Min Act: -0.1700
Data Index: 4198631 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.8505. Min Act: -0.1700
Data Index: 6501724 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.8505. Min Act: -0.1700
Data Index: 1937774 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.8505. Min Act: -0.1700
Data Index: 7401643 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.8192. Min Act: -0.1700
Data Index: 1179757 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.8505. Min Act: -0.1700
Data Index: 1283790 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.7567. Min Act: -0.1700
Data Index: 4391054 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.7255. Min Act: -0.1700
Data Index: 7154825 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.7255. Min Act: -0.1700
Data Index: 7521110 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.7255. Min Act: -0.1700
Data Index: 3621454 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.7255. Min Act: -0.1700
Data Index: 8734092 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.7255. Min Act: -0.1700
Data Index: 6276779 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.6942. Min Act: -0.1700
Data Index: 2254899 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.6942. Min Act: -0.1700
Data Index: 5793653 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.6630. Min Act: -0.1700
Data Index: 4791727 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3192. Min Range: -7.3192
Max Act: 6.6630. Min Act: -0.1700
Data Index: 7273386 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19