Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.8684. Min Act: -0.1700
Data Index: 7647085 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.8372. Min Act: -0.1700
Data Index: 7942652 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.8059. Min Act: -0.1700
Data Index: 6698454 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.5872. Min Act: -0.1700
Data Index: 5801029 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.5559. Min Act: -0.1700
Data Index: 3437677 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.5247. Min Act: -0.1700
Data Index: 2278596 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.5247. Min Act: -0.1700
Data Index: 5766367 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4934. Min Act: -0.1700
Data Index: 8576618 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4934. Min Act: -0.1700
Data Index: 7855471 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4934. Min Act: -0.1700
Data Index: 4525063 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4622. Min Act: -0.1700
Data Index: 174437 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4622. Min Act: -0.1700
Data Index: 4872746 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.4309. Min Act: -0.1700
Data Index: 8577665 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3997. Min Act: -0.1700
Data Index: 8082092 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3684. Min Act: -0.1700
Data Index: 2716278 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3684. Min Act: -0.1700
Data Index: 5859413 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3372. Min Act: -0.1700
Data Index: 5584478 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3372. Min Act: -0.1700
Data Index: 7889759 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.3059. Min Act: -0.1700
Data Index: 5766368 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8684. Min Range: -7.8684
Max Act: 7.2747. Min Act: -0.1700
Data Index: 1238307 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19