Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1300 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.9386. Min Act: -0.1700
Data Index: 8149813 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.5011. Min Act: -0.1700
Data Index: 2026432 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.4698. Min Act: -0.1700
Data Index: 710642 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.3761. Min Act: -0.1700
Data Index: 2026431 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.3448. Min Act: -0.1700
Data Index: 5683246 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.3448. Min Act: -0.1700
Data Index: 1855545 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.3448. Min Act: -0.1700
Data Index: 8641175 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.2511. Min Act: -0.1700
Data Index: 4497705 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.2511. Min Act: -0.1700
Data Index: 1827680 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.2198. Min Act: -0.1700
Data Index: 4121752 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.1573. Min Act: -0.1700
Data Index: 8478257 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.1573. Min Act: -0.1700
Data Index: 651676 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.1573. Min Act: -0.1700
Data Index: 5878865 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.0948. Min Act: -0.1700
Data Index: 8213275 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.1261. Min Act: -0.1700
Data Index: 5001204 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.0948. Min Act: -0.1700
Data Index: 6375779 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.0948. Min Act: -0.1700
Data Index: 1784441 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.0948. Min Act: -0.1700
Data Index: 5399845 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.0948. Min Act: -0.1700
Data Index: 883018 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9386. Min Range: -6.9386
Max Act: 6.0948. Min Act: -0.1700
Data Index: 7580058 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19