Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.7775. Min Act: -0.1700
Data Index: 6502823 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.7775. Min Act: -0.1700
Data Index: 6195067 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.8088. Min Act: -0.1700
Data Index: 4055683 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.7463. Min Act: -0.1700
Data Index: 4055685 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.5275. Min Act: -0.1700
Data Index: 8205492 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.4650. Min Act: -0.1700
Data Index: 6600342 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.4338. Min Act: -0.1700
Data Index: 8285396 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.4025. Min Act: -0.1700
Data Index: 5733629 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.3713. Min Act: -0.1700
Data Index: 2551533 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.3400. Min Act: -0.1700
Data Index: 2591549 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.3088. Min Act: -0.1700
Data Index: 4207146 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.3088. Min Act: -0.1700
Data Index: 2743020 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.3088. Min Act: -0.1700
Data Index: 1574205 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.2150. Min Act: -0.1700
Data Index: 1204035 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.1838. Min Act: -0.1700
Data Index: 4445253 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.2150. Min Act: -0.1700
Data Index: 1869861 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.1213. Min Act: -0.1700
Data Index: 6673929 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.1525. Min Act: -0.1700
Data Index: 8271891 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.0588. Min Act: -0.1700
Data Index: 6233291 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8088. Min Range: -6.8088
Max Act: 6.0900. Min Act: -0.1700
Data Index: 6444536 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19