Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2425 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0024. Min Range: -6.0024
Max Act: 6.0024. Min Act: -0.1700
Data Index: 305239 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.7524. Min Act: -0.1700
Data Index: 8127187 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.7524. Min Act: -0.1700
Data Index: 1679074 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.7212. Min Act: -0.1700
Data Index: 2911508 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.6587. Min Act: -0.1700
Data Index: 834716 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.6587. Min Act: -0.1700
Data Index: 6016572 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.5962. Min Act: -0.1700
Data Index: 5995961 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.5649. Min Act: -0.1700
Data Index: 2495722 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.5649. Min Act: -0.1700
Data Index: 5938358 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.5649. Min Act: -0.1700
Data Index: 7931790 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.5649. Min Act: -0.1700
Data Index: 724904 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.5337. Min Act: -0.1700
Data Index: 7577861 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.5024. Min Act: -0.1700
Data Index: 51778 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.5024. Min Act: -0.1700
Data Index: 7989803 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.4712. Min Act: -0.1700
Data Index: 6291935 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.4712. Min Act: -0.1700
Data Index: 4141099 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.4712. Min Act: -0.1700
Data Index: 3335380 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.4712. Min Act: -0.1700
Data Index: 5638643 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.4712. Min Act: -0.1700
Data Index: 4286971 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0024. Min Range: -6.0024
Max Act: 5.4399. Min Act: -0.1700
Data Index: 1152597 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19