Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3094 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3375. Min Range: -9.3375
Max Act: 9.3375. Min Act: -0.1700
Data Index: 6822653 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3375. Min Range: -9.3375
Max Act: 8.7125. Min Act: -0.1700
Data Index: 3185538 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3375. Min Range: -9.3375
Max Act: 8.3375. Min Act: -0.1700
Data Index: 805466 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3375. Min Range: -9.3375
Max Act: 8.0250. Min Act: -0.1700
Data Index: 4489881 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3375. Min Range: -9.3375
Max Act: 8.0250. Min Act: -0.1700
Data Index: 1668824 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3375. Min Range: -9.3375
Max Act: 8.0250. Min Act: -0.1700
Data Index: 6823315 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.9000. Min Act: -0.1700
Data Index: 4449572 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.9625. Min Act: -0.1700
Data Index: 874374 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.9625. Min Act: -0.1700
Data Index: 5127882 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.9000. Min Act: -0.1700
Data Index: 8322644 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.9000. Min Act: -0.1700
Data Index: 5127881 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.9000. Min Act: -0.1700
Data Index: 1832973 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.9625. Min Act: -0.1700
Data Index: 4970583 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.8375. Min Act: -0.1700
Data Index: 7744132 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.8375. Min Act: -0.1700
Data Index: 7952363 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.7750. Min Act: -0.1700
Data Index: 5712118 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.8375. Min Act: -0.1700
Data Index: 6847604 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.8375. Min Act: -0.1700
Data Index: 4832220 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.7750. Min Act: -0.1700
Data Index: 1609873 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3375. Min Range: -9.3375
Max Act: 7.7750. Min Act: -0.1700
Data Index: 6367155 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19