Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.7288. Min Act: -0.1700
Data Index: 106844 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.7601. Min Act: -0.1700
Data Index: 3860536 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.6976. Min Act: -0.1700
Data Index: 8023970 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.6038. Min Act: -0.1700
Data Index: 1240012 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5726. Min Act: -0.1700
Data Index: 5080701 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.6038. Min Act: -0.1700
Data Index: 515419 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5726. Min Act: -0.1700
Data Index: 4440696 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5413. Min Act: -0.1700
Data Index: 3848323 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5413. Min Act: -0.1700
Data Index: 704141 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5413. Min Act: -0.1700
Data Index: 6051746 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5413. Min Act: -0.1700
Data Index: 8293936 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5413. Min Act: -0.1700
Data Index: 5365029 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5101. Min Act: -0.1700
Data Index: 4445231 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5101. Min Act: -0.1700
Data Index: 7756756 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.5101. Min Act: -0.1700
Data Index: 5225780 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.4788. Min Act: -0.1700
Data Index: 7514050 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.4788. Min Act: -0.1700
Data Index: 6276649 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.4788. Min Act: -0.1700
Data Index: 6092672 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.4163. Min Act: -0.1700
Data Index: 3007360 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7601. Min Range: -5.7601
Max Act: 5.4476. Min Act: -0.1700
Data Index: 2093275 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19