Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.2964. Min Act: -0.1700
Data Index: 8676835 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.2339. Min Act: -0.1700
Data Index: 2603703 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.2027. Min Act: -0.1700
Data Index: 6453592 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.1089. Min Act: -0.1700
Data Index: 8305925 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.0777. Min Act: -0.1700
Data Index: 711183 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.0464. Min Act: -0.1700
Data Index: 1862299 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.0152. Min Act: -0.1700
Data Index: 225038 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.0152. Min Act: -0.1700
Data Index: 7136638 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.0152. Min Act: -0.1700
Data Index: 7044155 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2964. Min Range: -5.2964
Max Act: 5.0152. Min Act: -0.1700
Data Index: 1564026 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9839. Min Act: -0.1700
Data Index: 918773 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9839. Min Act: -0.1700
Data Index: 6818310 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9839. Min Act: -0.1700
Data Index: 8543419 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9839. Min Act: -0.1700
Data Index: 6542760 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9839. Min Act: -0.1700
Data Index: 8252828 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9527. Min Act: -0.1700
Data Index: 5672043 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9527. Min Act: -0.1700
Data Index: 8361968 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9527. Min Act: -0.1700
Data Index: 8370009 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9527. Min Act: -0.1700
Data Index: 4497054 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2964. Min Range: -5.2964
Max Act: 4.9527. Min Act: -0.1700
Data Index: 2041937 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19