Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.2379. Min Act: -0.1700
Data Index: 8024027 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.1129. Min Act: -0.1700
Data Index: 8330114 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0816. Min Act: -0.1700
Data Index: 7474488 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0816. Min Act: -0.1700
Data Index: 7766473 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0816. Min Act: -0.1700
Data Index: 2798483 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0816. Min Act: -0.1700
Data Index: 4330720 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0504. Min Act: -0.1700
Data Index: 922168 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0504. Min Act: -0.1700
Data Index: 7822411 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0504. Min Act: -0.1700
Data Index: 6324784 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0504. Min Act: -0.1700
Data Index: 4726312 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0191. Min Act: -0.1700
Data Index: 4233148 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0191. Min Act: -0.1700
Data Index: 4278379 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0504. Min Act: -0.1700
Data Index: 8230650 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0191. Min Act: -0.1700
Data Index: 3003115 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2379. Min Range: -5.2379
Max Act: 5.0191. Min Act: -0.1700
Data Index: 1401187 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 7599776 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 1078433 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 2234467 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 7822309 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2379. Min Range: -5.2379
Max Act: 4.9879. Min Act: -0.1700
Data Index: 5078435 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19