Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5883. Min Range: -9.5883
Max Act: 9.5883. Min Act: -0.1700
Data Index: 5113198 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5883. Min Range: -9.5883
Max Act: 9.2133. Min Act: -0.1700
Data Index: 2123394 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5883. Min Range: -9.5883
Max Act: 9.2133. Min Act: -0.1700
Data Index: 2784120 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5883. Min Range: -9.5883
Max Act: 9.0883. Min Act: -0.1700
Data Index: 4030501 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5883. Min Range: -9.5883
Max Act: 9.0883. Min Act: -0.1700
Data Index: 4898322 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5883. Min Range: -9.5883
Max Act: 9.0883. Min Act: -0.1700
Data Index: 2688641 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5883. Min Range: -9.5883
Max Act: 9.0883. Min Act: -0.1700
Data Index: 7024786 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5883. Min Range: -9.5883
Max Act: 9.0883. Min Act: -0.1700
Data Index: 841740 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5883. Min Range: -9.5883
Max Act: 9.0258. Min Act: -0.1700
Data Index: 2520807 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9633. Min Act: -0.1700
Data Index: 3358340 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9633. Min Act: -0.1700
Data Index: 4333855 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9633. Min Act: -0.1700
Data Index: 4960485 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9633. Min Act: -0.1700
Data Index: 5907314 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9008. Min Act: -0.1700
Data Index: 7997000 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9633. Min Act: -0.1700
Data Index: 1492792 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9633. Min Act: -0.1700
Data Index: 6732712 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9008. Min Act: -0.1700
Data Index: 5217962 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9008. Min Act: -0.1700
Data Index: 7398884 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.8383. Min Act: -0.1700
Data Index: 4360498 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5883. Min Range: -9.5883
Max Act: 8.9008. Min Act: -0.1700
Data Index: 2894219 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19