Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 244 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0131. Min Range: -7.0131
Max Act: 7.0131. Min Act: -0.1700
Data Index: 8357885 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.9193. Min Act: -0.1700
Data Index: 3145455 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.8256. Min Act: -0.1700
Data Index: 8663157 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.7318. Min Act: -0.1700
Data Index: 5536573 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.7318. Min Act: -0.1700
Data Index: 791931 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.7006. Min Act: -0.1700
Data Index: 2359842 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.5756. Min Act: -0.1700
Data Index: 7646407 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.5756. Min Act: -0.1700
Data Index: 3354440 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.5443. Min Act: -0.1700
Data Index: 2686414 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.5131. Min Act: -0.1700
Data Index: 7204842 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.5131. Min Act: -0.1700
Data Index: 3759411 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.5131. Min Act: -0.1700
Data Index: 8062826 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.4506. Min Act: -0.1700
Data Index: 1746065 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.4506. Min Act: -0.1700
Data Index: 1523457 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.5131. Min Act: -0.1700
Data Index: 5306385 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.4506. Min Act: -0.1700
Data Index: 26922 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.4818. Min Act: -0.1700
Data Index: 2141681 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.4818. Min Act: -0.1700
Data Index: 1622197 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.4193. Min Act: -0.1700
Data Index: 5574448 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0131. Min Range: -7.0131
Max Act: 6.3881. Min Act: -0.1700
Data Index: 3295023 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19