Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4338 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6584. Min Range: -7.6584
Max Act: 7.6584. Min Act: -0.1700
Data Index: 2807433 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6584. Min Range: -7.6584
Max Act: 7.4396. Min Act: -0.1700
Data Index: 8797874 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6584. Min Range: -7.6584
Max Act: 7.3146. Min Act: -0.1700
Data Index: 253112 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6584. Min Range: -7.6584
Max Act: 7.2521. Min Act: -0.1700
Data Index: 7007627 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6584. Min Range: -7.6584
Max Act: 7.0334. Min Act: -0.1700
Data Index: 7866460 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6584. Min Range: -7.6584
Max Act: 7.0021. Min Act: -0.1700
Data Index: 3673939 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.9709. Min Act: -0.1700
Data Index: 8328171 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.9709. Min Act: -0.1700
Data Index: 90913 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.9084. Min Act: -0.1700
Data Index: 2061202 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.9084. Min Act: -0.1700
Data Index: 1070299 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.8459. Min Act: -0.1700
Data Index: 8781894 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.8146. Min Act: -0.1700
Data Index: 6112148 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.8146. Min Act: -0.1700
Data Index: 2123090 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.8146. Min Act: -0.1700
Data Index: 2854693 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.8146. Min Act: -0.1700
Data Index: 8270463 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.8459. Min Act: -0.1700
Data Index: 5855806 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.7521. Min Act: -0.1700
Data Index: 7285910 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.8146. Min Act: -0.1700
Data Index: 4877694 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.7834. Min Act: -0.1700
Data Index: 5767068 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6584. Min Range: -7.6584
Max Act: 6.7834. Min Act: -0.1700
Data Index: 1860760 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19