Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2115. Min Range: -6.2115
Max Act: 6.2115. Min Act: -0.1700
Data Index: 6810527 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2115. Min Range: -6.2115
Max Act: 6.0240. Min Act: -0.1700
Data Index: 8315577 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.9927. Min Act: -0.1700
Data Index: 8449610 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.9615. Min Act: -0.1700
Data Index: 3198245 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.8990. Min Act: -0.1700
Data Index: 3132326 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.8365. Min Act: -0.1700
Data Index: 6456607 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.8677. Min Act: -0.1700
Data Index: 2610767 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.8677. Min Act: -0.1700
Data Index: 2389211 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.8365. Min Act: -0.1700
Data Index: 5424053 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.8365. Min Act: -0.1700
Data Index: 4342294 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.8052. Min Act: -0.1700
Data Index: 6590457 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.8365. Min Act: -0.1700
Data Index: 5844612 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.7740. Min Act: -0.1700
Data Index: 3932481 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.7740. Min Act: -0.1700
Data Index: 6894503 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.7740. Min Act: -0.1700
Data Index: 6177269 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.7740. Min Act: -0.1700
Data Index: 426700 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.7427. Min Act: -0.1700
Data Index: 7735673 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.7115. Min Act: -0.1700
Data Index: 7580011 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.7115. Min Act: -0.1700
Data Index: 6776669 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2115. Min Range: -6.2115
Max Act: 5.7115. Min Act: -0.1700
Data Index: 1498876 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19