Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 920 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.6599. Min Act: -0.1700
Data Index: 5116996 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.5974. Min Act: -0.1700
Data Index: 1595001 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.3474. Min Act: -0.1700
Data Index: 3992329 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.2536. Min Act: -0.1700
Data Index: 7767444 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.2224. Min Act: -0.1700
Data Index: 4678341 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.1911. Min Act: -0.1700
Data Index: 7735920 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.1286. Min Act: -0.1700
Data Index: 979931 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.1286. Min Act: -0.1700
Data Index: 3812771 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.1599. Min Act: -0.1700
Data Index: 4781796 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.0661. Min Act: -0.1700
Data Index: 6498360 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.0661. Min Act: -0.1700
Data Index: 7245770 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.0349. Min Act: -0.1700
Data Index: 7451182 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.0036. Min Act: -0.1700
Data Index: 2280574 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6599. Min Range: -5.6599
Max Act: 5.0036. Min Act: -0.1700
Data Index: 2049755 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6599. Min Range: -5.6599
Max Act: 4.9724. Min Act: -0.1700
Data Index: 7162952 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6599. Min Range: -5.6599
Max Act: 4.9724. Min Act: -0.1700
Data Index: 4998249 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6599. Min Range: -5.6599
Max Act: 4.9411. Min Act: -0.1700
Data Index: 1729035 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6599. Min Range: -5.6599
Max Act: 4.9411. Min Act: -0.1700
Data Index: 1316813 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6599. Min Range: -5.6599
Max Act: 4.9411. Min Act: -0.1700
Data Index: 2115143 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6599. Min Range: -5.6599
Max Act: 4.9411. Min Act: -0.1700
Data Index: 3504789 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19