Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4709 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.5658. Min Act: -0.1700
Data Index: 3618325 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.5345. Min Act: -0.1700
Data Index: 5187404 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.5345. Min Act: -0.1700
Data Index: 8790482 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.5033. Min Act: -0.1700
Data Index: 6796833 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.5033. Min Act: -0.1700
Data Index: 8277664 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.5033. Min Act: -0.1699
Data Index: 5242665 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4720. Min Act: -0.1700
Data Index: 2381002 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4720. Min Act: -0.1700
Data Index: 8368973 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4720. Min Act: -0.1700
Data Index: 3101674 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4720. Min Act: -0.1700
Data Index: 682420 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4720. Min Act: -0.1700
Data Index: 2136325 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4720. Min Act: -0.1700
Data Index: 8663966 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4408. Min Act: -0.1700
Data Index: 12534 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4408. Min Act: -0.1700
Data Index: 3645993 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4408. Min Act: -0.1700
Data Index: 3375508 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4408. Min Act: -0.1700
Data Index: 813737 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4408. Min Act: -0.1700
Data Index: 5420993 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4095. Min Act: -0.1700
Data Index: 7980695 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4095. Min Act: -0.1700
Data Index: 831667 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5658. Min Range: -5.5658
Max Act: 5.4095. Min Act: -0.1700
Data Index: 4307207 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19