Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1018 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3677. Min Range: -5.3677
Max Act: 5.3677. Min Act: -0.1700
Data Index: 5667217 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3677. Min Range: -5.3677
Max Act: 5.0240. Min Act: -0.1700
Data Index: 3398568 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.8365. Min Act: -0.1700
Data Index: 4275357 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.7115. Min Act: -0.1700
Data Index: 706758 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.7427. Min Act: -0.1700
Data Index: 7026075 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.6802. Min Act: -0.1700
Data Index: 618869 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.6490. Min Act: -0.1700
Data Index: 506162 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.6490. Min Act: -0.1700
Data Index: 2491870 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.6177. Min Act: -0.1700
Data Index: 5404312 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.6177. Min Act: -0.1700
Data Index: 5037037 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.6177. Min Act: -0.1700
Data Index: 388218 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.6177. Min Act: -0.1700
Data Index: 5254630 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.6177. Min Act: -0.1700
Data Index: 732418 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.5552. Min Act: -0.1700
Data Index: 6766383 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.5552. Min Act: -0.1700
Data Index: 2884250 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.5552. Min Act: -0.1700
Data Index: 8254927 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.5552. Min Act: -0.1700
Data Index: 7932892 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.5552. Min Act: -0.1700
Data Index: 3371751 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.5240. Min Act: -0.1700
Data Index: 379193 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3677. Min Range: -5.3677
Max Act: 4.5240. Min Act: -0.1700
Data Index: 4528003 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19