Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.6538. Min Act: -0.1700
Data Index: 926061 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.6226. Min Act: -0.1700
Data Index: 8131402 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.4351. Min Act: -0.1700
Data Index: 5104204 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.3726. Min Act: -0.1700
Data Index: 998824 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.3726. Min Act: -0.1700
Data Index: 1647573 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.3101. Min Act: -0.1700
Data Index: 7296329 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.2163. Min Act: -0.1700
Data Index: 6145312 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.1851. Min Act: -0.1700
Data Index: 1074574 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.1851. Min Act: -0.1700
Data Index: 8311776 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.1538. Min Act: -0.1700
Data Index: 4671977 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.1538. Min Act: -0.1700
Data Index: 245931 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.0913. Min Act: -0.1700
Data Index: 8043952 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.0288. Min Act: -0.1700
Data Index: 8630638 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6538. Min Range: -5.6538
Max Act: 5.0601. Min Act: -0.1700
Data Index: 6808141 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6538. Min Range: -5.6538
Max Act: 4.9663. Min Act: -0.1700
Data Index: 2878415 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6538. Min Range: -5.6538
Max Act: 4.9038. Min Act: -0.1700
Data Index: 343009 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6538. Min Range: -5.6538
Max Act: 4.9663. Min Act: -0.1700
Data Index: 3067002 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6538. Min Range: -5.6538
Max Act: 4.9038. Min Act: -0.1700
Data Index: 6555288 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6538. Min Range: -5.6538
Max Act: 4.8726. Min Act: -0.1700
Data Index: 3363468 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6538. Min Range: -5.6538
Max Act: 4.8413. Min Act: -0.1700
Data Index: 8690325 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19