Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2211 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.4120. Min Act: -0.1700
Data Index: 4780982 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.3182. Min Act: -0.1700
Data Index: 4338771 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.2870. Min Act: -0.1700
Data Index: 7589838 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.2870. Min Act: -0.1700
Data Index: 1658983 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.2557. Min Act: -0.1700
Data Index: 2167198 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.2245. Min Act: -0.1700
Data Index: 5420362 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1932. Min Act: -0.1700
Data Index: 7293766 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1620. Min Act: -0.1700
Data Index: 2819522 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1620. Min Act: -0.1700
Data Index: 4219871 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1620. Min Act: -0.1700
Data Index: 3979971 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1620. Min Act: -0.1700
Data Index: 6402929 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1620. Min Act: -0.1700
Data Index: 4339211 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1307. Min Act: -0.1700
Data Index: 6560607 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1307. Min Act: -0.1700
Data Index: 2618888 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.0995. Min Act: -0.1700
Data Index: 8258677 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1307. Min Act: -0.1700
Data Index: 2211979 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1307. Min Act: -0.1700
Data Index: 7250636 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1307. Min Act: -0.1700
Data Index: 2873882 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.1307. Min Act: -0.1700
Data Index: 4849149 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4120. Min Range: -5.4120
Max Act: 5.0995. Min Act: -0.1700
Data Index: 3009800 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19