Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.2592. Min Act: -0.1700
Data Index: 7033380 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.2280. Min Act: -0.1700
Data Index: 1385561 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.1967. Min Act: -0.1700
Data Index: 346844 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.1342. Min Act: -0.1700
Data Index: 4916330 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.1030. Min Act: -0.1700
Data Index: 1941728 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.0092. Min Act: -0.1700
Data Index: 8692134 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.0092. Min Act: -0.1700
Data Index: 2364255 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.0092. Min Act: -0.1700
Data Index: 3519584 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.9780. Min Act: -0.1700
Data Index: 1272146 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.0092. Min Act: -0.1700
Data Index: 1503202 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2592. Min Range: -7.2592
Max Act: 7.0092. Min Act: -0.1700
Data Index: 1158204 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.9780. Min Act: -0.1700
Data Index: 8119103 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.9780. Min Act: -0.1700
Data Index: 606450 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.9780. Min Act: -0.1700
Data Index: 1719246 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.9467. Min Act: -0.1700
Data Index: 7047086 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.9467. Min Act: -0.1700
Data Index: 2663088 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.9467. Min Act: -0.1700
Data Index: 939461 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.9155. Min Act: -0.1700
Data Index: 2917525 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.8842. Min Act: -0.1700
Data Index: 1893881 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2592. Min Range: -7.2592
Max Act: 6.9155. Min Act: -0.1700
Data Index: 1756924 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19