Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 696 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.7264. Min Act: -0.1700
Data Index: 4636853 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.6014. Min Act: -0.1700
Data Index: 1298148 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.4764. Min Act: -0.1700
Data Index: 5345393 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.4764. Min Act: -0.1700
Data Index: 4432246 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.4764. Min Act: -0.1700
Data Index: 6025385 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.3514. Min Act: -0.1700
Data Index: 5187909 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.3514. Min Act: -0.1700
Data Index: 2158445 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.3201. Min Act: -0.1700
Data Index: 5989819 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.2889. Min Act: -0.1700
Data Index: 2319851 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.2889. Min Act: -0.1700
Data Index: 5602059 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.2889. Min Act: -0.1700
Data Index: 6274594 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.2576. Min Act: -0.1700
Data Index: 7493448 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.2264. Min Act: -0.1700
Data Index: 7603106 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.2576. Min Act: -0.1700
Data Index: 7494206 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.2576. Min Act: -0.1700
Data Index: 4228189 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.2576. Min Act: -0.1700
Data Index: 2288431 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.1951. Min Act: -0.1700
Data Index: 964172 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.1951. Min Act: -0.1700
Data Index: 738175 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.1951. Min Act: -0.1700
Data Index: 2838738 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.1639. Min Act: -0.1700
Data Index: 7235351 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19