Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1950 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.4700. Min Act: -0.1700
Data Index: 4793092 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.2825. Min Act: -0.1700
Data Index: 3281602 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.2825. Min Act: -0.1700
Data Index: 5447763 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.2825. Min Act: -0.1700
Data Index: 6124061 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.2200. Min Act: -0.1700
Data Index: 2663074 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 3533250 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1887. Min Act: -0.1700
Data Index: 8745407 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1887. Min Act: -0.1700
Data Index: 7681111 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1887. Min Act: -0.1700
Data Index: 576965 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1887. Min Act: -0.1700
Data Index: 1273792 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 7908367 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 4769221 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 6610403 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 3281601 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 5934658 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 3861910 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 3684703 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 5237742 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 324798 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 3533253 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19