Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5216 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0305. Min Range: -7.0305
Max Act: 7.0305. Min Act: -0.1700
Data Index: 913433 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.7805. Min Act: -0.1700
Data Index: 1112152 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.4055. Min Act: -0.1700
Data Index: 353090 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.1555. Min Act: -0.1700
Data Index: 3192994 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.0930. Min Act: -0.1700
Data Index: 7861867 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.0618. Min Act: -0.1700
Data Index: 1081616 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.0618. Min Act: -0.1700
Data Index: 4195548 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.0618. Min Act: -0.1700
Data Index: 526633 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.0618. Min Act: -0.1700
Data Index: 1564424 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.0618. Min Act: -0.1700
Data Index: 2611184 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.0305. Min Act: -0.1700
Data Index: 4982963 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0305. Min Range: -7.0305
Max Act: 5.9993. Min Act: -0.1700
Data Index: 8717088 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0305. Min Range: -7.0305
Max Act: 6.0305. Min Act: -0.1700
Data Index: 8020013 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0305. Min Range: -7.0305
Max Act: 5.9368. Min Act: -0.1700
Data Index: 526632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0305. Min Range: -7.0305
Max Act: 5.9680. Min Act: -0.1700
Data Index: 3433205 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0305. Min Range: -7.0305
Max Act: 5.9680. Min Act: -0.1700
Data Index: 5883185 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0305. Min Range: -7.0305
Max Act: 5.9680. Min Act: -0.1700
Data Index: 5855622 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0305. Min Range: -7.0305
Max Act: 5.9368. Min Act: -0.1700
Data Index: 6466197 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0305. Min Range: -7.0305
Max Act: 5.9368. Min Act: -0.1700
Data Index: 2965096 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0305. Min Range: -7.0305
Max Act: 5.9368. Min Act: -0.1700
Data Index: 5000036 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19