Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0924. Min Range: -6.0924
Max Act: 6.0924. Min Act: -0.1700
Data Index: 2135354 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0924. Min Range: -6.0924
Max Act: 6.0299. Min Act: -0.1700
Data Index: 3183216 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.9987. Min Act: -0.1700
Data Index: 5011266 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.9674. Min Act: -0.1700
Data Index: 134939 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.9362. Min Act: -0.1700
Data Index: 4383377 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.9362. Min Act: -0.1700
Data Index: 7636480 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.8737. Min Act: -0.1700
Data Index: 5511118 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.8424. Min Act: -0.1700
Data Index: 6034419 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.8112. Min Act: -0.1700
Data Index: 4084079 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.8112. Min Act: -0.1700
Data Index: 84147 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.7799. Min Act: -0.1700
Data Index: 5536592 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.7799. Min Act: -0.1700
Data Index: 4924436 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.7487. Min Act: -0.1700
Data Index: 6630871 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.7487. Min Act: -0.1700
Data Index: 2885326 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.7174. Min Act: -0.1700
Data Index: 5664974 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.7487. Min Act: -0.1700
Data Index: 2595185 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.6862. Min Act: -0.1700
Data Index: 6279194 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.7174. Min Act: -0.1700
Data Index: 4878395 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.6862. Min Act: -0.1700
Data Index: 1227289 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0924. Min Range: -6.0924
Max Act: 5.6862. Min Act: -0.1700
Data Index: 1098607 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19