Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.4524. Min Act: -0.1700
Data Index: 8266315 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2962. Min Act: -0.1700
Data Index: 8396924 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2962. Min Act: -0.1700
Data Index: 56416 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2649. Min Act: -0.1700
Data Index: 8395452 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2649. Min Act: -0.1700
Data Index: 4672449 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 2758467 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 2565472 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 2102645 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 3643618 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1697
Data Index: 1476881 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 881559 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 3415042 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 2639794 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 2067986 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 569247 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1696
Data Index: 2836240 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 452182 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 93080 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1697
Data Index: 2034660 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.2337. Min Act: -0.1700
Data Index: 2801401 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19