Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5883 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.9413. Min Act: -0.1700
Data Index: 3778368 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.9413. Min Act: -0.1700
Data Index: 3359784 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.8476. Min Act: -0.1700
Data Index: 3039284 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7851. Min Act: -0.1700
Data Index: 6631386 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 7332348 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.7226. Min Act: -0.1700
Data Index: 3745718 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 2833065 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6601. Min Act: -0.1700
Data Index: 1412400 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 4033320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 4405871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 3203904 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 3716283 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 7218182 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.6288. Min Act: -0.1700
Data Index: 8293288 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5976. Min Act: -0.1700
Data Index: 2833067 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5976. Min Act: -0.1700
Data Index: 1391022 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5976. Min Act: -0.1700
Data Index: 8019423 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5663. Min Act: -0.1700
Data Index: 6207717 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5663. Min Act: -0.1700
Data Index: 3479608 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9413. Min Range: -4.9413
Max Act: 4.5663. Min Act: -0.1700
Data Index: 2594758 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19