Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1632 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5647. Min Range: -7.5647
Max Act: 7.5647. Min Act: -0.1700
Data Index: 336038 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5647. Min Range: -7.5647
Max Act: 7.2210. Min Act: -0.1700
Data Index: 7833615 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5647. Min Range: -7.5647
Max Act: 7.0960. Min Act: -0.1694
Data Index: 5986734 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5647. Min Range: -7.5647
Max Act: 7.0960. Min Act: -0.1700
Data Index: 8596726 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5647. Min Range: -7.5647
Max Act: 7.0335. Min Act: -0.1700
Data Index: 6492072 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5647. Min Range: -7.5647
Max Act: 7.0335. Min Act: -0.1693
Data Index: 3312892 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5647. Min Range: -7.5647
Max Act: 7.0022. Min Act: -0.1700
Data Index: 2197095 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5647. Min Range: -7.5647
Max Act: 7.0022. Min Act: -0.1700
Data Index: 2635776 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.9710. Min Act: -0.1700
Data Index: 5794595 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.9085. Min Act: -0.1698
Data Index: 4578734 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.9085. Min Act: -0.1700
Data Index: 2964937 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.9085. Min Act: -0.1700
Data Index: 3652005 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.8772. Min Act: -0.1700
Data Index: 41478 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.8772. Min Act: -0.1700
Data Index: 433237 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.8772. Min Act: -0.1700
Data Index: 7418757 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.8460. Min Act: -0.1700
Data Index: 2458853 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.8460. Min Act: -0.1700
Data Index: 2804404 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.8772. Min Act: -0.1700
Data Index: 8281478 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.8772. Min Act: -0.1700
Data Index: 2917354 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5647. Min Range: -7.5647
Max Act: 6.8147. Min Act: -0.1700
Data Index: 3931266 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19