Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.9810. Min Act: -0.1700
Data Index: 8455259 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.9185. Min Act: -0.1700
Data Index: 8547574 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8873. Min Act: -0.1700
Data Index: 5903175 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8560. Min Act: -0.1700
Data Index: 2387904 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8248. Min Act: -0.1700
Data Index: 2158615 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.8248. Min Act: -0.1700
Data Index: 7133734 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7623. Min Act: -0.1700
Data Index: 8597013 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7623. Min Act: -0.1700
Data Index: 3011436 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7623. Min Act: -0.1700
Data Index: 2424160 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7623. Min Act: -0.1700
Data Index: 2518990 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7623. Min Act: -0.1700
Data Index: 7206359 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7310. Min Act: -0.1700
Data Index: 2131681 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7310. Min Act: -0.1700
Data Index: 8544287 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7310. Min Act: -0.1700
Data Index: 1813149 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7310. Min Act: -0.1700
Data Index: 647100 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.7310. Min Act: -0.1700
Data Index: 211800 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.6998. Min Act: -0.1700
Data Index: 2601541 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.6998. Min Act: -0.1700
Data Index: 7225051 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.6998. Min Act: -0.1700
Data Index: 5598000 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9810. Min Range: -4.9810
Max Act: 4.6998. Min Act: -0.1700
Data Index: 2197644 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19