Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6274 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.3052. Min Act: -0.1700
Data Index: 6739753 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.3365. Min Act: -0.1700
Data Index: 4169582 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.3365. Min Act: -0.1700
Data Index: 4006274 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.3052. Min Act: -0.1700
Data Index: 3169341 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.3052. Min Act: -0.1700
Data Index: 818851 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.2740. Min Act: -0.1700
Data Index: 821855 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.2115. Min Act: -0.1700
Data Index: 7555667 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.2427. Min Act: -0.1700
Data Index: 4480265 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.2115. Min Act: -0.1700
Data Index: 1613359 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.2115. Min Act: -0.1700
Data Index: 8570104 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1802. Min Act: -0.1700
Data Index: 5351455 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1802. Min Act: -0.1700
Data Index: 3811001 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1802. Min Act: -0.1700
Data Index: 1109216 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1802. Min Act: -0.1700
Data Index: 8276712 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1802. Min Act: -0.1700
Data Index: 1973593 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1802. Min Act: -0.1700
Data Index: 7029928 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1802. Min Act: -0.1700
Data Index: 3125081 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1490. Min Act: -0.1700
Data Index: 6908881 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1802. Min Act: -0.1700
Data Index: 673859 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3365. Min Range: -6.3365
Max Act: 6.1490. Min Act: -0.1700
Data Index: 5985264 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19