Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4151. Min Range: -9.4151
Max Act: 9.4151. Min Act: -0.1700
Data Index: 867249 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4151. Min Range: -9.4151
Max Act: 9.3526. Min Act: -0.1700
Data Index: 8399940 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4151. Min Range: -9.4151
Max Act: 9.2901. Min Act: -0.1700
Data Index: 2203218 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.8526. Min Act: -0.1700
Data Index: 2448184 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.6651. Min Act: -0.1700
Data Index: 1542820 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.6026. Min Act: -0.1700
Data Index: 535267 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.5401. Min Act: -0.1700
Data Index: 1161078 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.5401. Min Act: -0.1700
Data Index: 8286526 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.4776. Min Act: -0.1700
Data Index: 4938915 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.4776. Min Act: -0.1700
Data Index: 4022212 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.4776. Min Act: -0.1700
Data Index: 1926413 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.4151. Min Act: -0.1700
Data Index: 8328026 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.4151. Min Act: -0.1700
Data Index: 4987191 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.4151. Min Act: -0.1700
Data Index: 1944569 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.3526. Min Act: -0.1700
Data Index: 2542250 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.2901. Min Act: -0.1700
Data Index: 1664062 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.2901. Min Act: -0.1700
Data Index: 5988515 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.3526. Min Act: -0.1700
Data Index: 2564811 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.2276. Min Act: -0.1700
Data Index: 67617 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4151. Min Range: -9.4151
Max Act: 8.1651. Min Act: -0.1700
Data Index: 515547 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19