Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3224. Min Range: -6.3224
Max Act: 6.3224. Min Act: -0.1700
Data Index: 5390447 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3224. Min Range: -6.3224
Max Act: 6.2911. Min Act: -0.1700
Data Index: 7329254 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3224. Min Range: -6.3224
Max Act: 6.2911. Min Act: -0.1700
Data Index: 2214004 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3224. Min Range: -6.3224
Max Act: 6.2599. Min Act: -0.1700
Data Index: 3747882 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3224. Min Range: -6.3224
Max Act: 6.2599. Min Act: -0.1700
Data Index: 984561 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3224. Min Range: -6.3224
Max Act: 6.1661. Min Act: -0.1700
Data Index: 8662748 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3224. Min Range: -6.3224
Max Act: 6.1349. Min Act: -0.1700
Data Index: 3474192 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3224. Min Range: -6.3224
Max Act: 6.0099. Min Act: -0.1700
Data Index: 686112 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.9786. Min Act: -0.1700
Data Index: 2870940 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.9474. Min Act: -0.1700
Data Index: 2870941 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.8849. Min Act: -0.1700
Data Index: 6412298 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.6661. Min Act: -0.1700
Data Index: 6749879 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.6661. Min Act: -0.1700
Data Index: 576355 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.6349. Min Act: -0.1700
Data Index: 8698953 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.6349. Min Act: -0.1700
Data Index: 5961725 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.6036. Min Act: -0.1700
Data Index: 5735200 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.5724. Min Act: -0.1700
Data Index: 6330994 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.6036. Min Act: -0.1700
Data Index: 6089569 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.5724. Min Act: -0.1700
Data Index: 7601638 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3224. Min Range: -6.3224
Max Act: 5.5724. Min Act: -0.1700
Data Index: 6471184 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19