Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2758 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.9237. Min Act: -0.1700
Data Index: 2261825 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.8612. Min Act: -0.1700
Data Index: 2613934 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.7987. Min Act: -0.1700
Data Index: 8104285 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.7987. Min Act: -0.1700
Data Index: 6945598 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.6737. Min Act: -0.1700
Data Index: 117330 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.6737. Min Act: -0.1700
Data Index: 3954499 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.6112. Min Act: -0.1700
Data Index: 2476464 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.6112. Min Act: -0.1700
Data Index: 3135771 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.6112. Min Act: -0.1700
Data Index: 6748010 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.6112. Min Act: -0.1700
Data Index: 31031 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.5487. Min Act: -0.1700
Data Index: 7969570 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.5487. Min Act: -0.1700
Data Index: 140386 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.5487. Min Act: -0.1700
Data Index: 5646618 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.5487. Min Act: -0.1700
Data Index: 5710683 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.5175. Min Act: -0.1700
Data Index: 376552 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.5175. Min Act: -0.1700
Data Index: 3583558 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.4550. Min Act: -0.1700
Data Index: 7626382 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.5175. Min Act: -0.1700
Data Index: 8537303 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.4550. Min Act: -0.1700
Data Index: 5987074 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9237. Min Range: -7.9237
Max Act: 7.4862. Min Act: -0.1700
Data Index: 1668 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19