Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.4667. Min Act: -0.1700
Data Index: 6613019 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.4667. Min Act: -0.1700
Data Index: 5033357 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.4354. Min Act: -0.1700
Data Index: 3904132 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.2792. Min Act: -0.1700
Data Index: 7702983 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.2167. Min Act: -0.1700
Data Index: 2311512 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.1854. Min Act: -0.1700
Data Index: 3082731 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.1229. Min Act: -0.1700
Data Index: 4151971 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.1542. Min Act: -0.1700
Data Index: 1890336 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.1229. Min Act: -0.1700
Data Index: 3541352 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.1229. Min Act: -0.1700
Data Index: 3633932 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.1229. Min Act: -0.1700
Data Index: 4913942 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.1229. Min Act: -0.1700
Data Index: 8009755 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.0917. Min Act: -0.1700
Data Index: 3867532 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.1229. Min Act: -0.1700
Data Index: 4513325 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.0604. Min Act: -0.1700
Data Index: 876164 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.0917. Min Act: -0.1700
Data Index: 6225142 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.0604. Min Act: -0.1700
Data Index: 2100234 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.0604. Min Act: -0.1700
Data Index: 6244020 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4667. Min Range: -5.4667
Max Act: 5.0292. Min Act: -0.1700
Data Index: 5024406 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4667. Min Range: -5.4667
Max Act: 4.9979. Min Act: -0.1700
Data Index: 2946289 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19