Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3124 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2213. Min Range: -5.2213
Max Act: 5.2213. Min Act: -0.1700
Data Index: 60126 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2213. Min Range: -5.2213
Max Act: 5.0963. Min Act: -0.1700
Data Index: 549361 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2213. Min Range: -5.2213
Max Act: 5.0963. Min Act: -0.1700
Data Index: 16084 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2213. Min Range: -5.2213
Max Act: 5.0651. Min Act: -0.1700
Data Index: 6970413 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2213. Min Range: -5.2213
Max Act: 5.0651. Min Act: -0.1700
Data Index: 8694459 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2213. Min Range: -5.2213
Max Act: 5.0338. Min Act: -0.1700
Data Index: 8173624 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2213. Min Range: -5.2213
Max Act: 5.0338. Min Act: -0.1700
Data Index: 5666144 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2213. Min Range: -5.2213
Max Act: 5.0338. Min Act: -0.1700
Data Index: 8173630 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2213. Min Range: -5.2213
Max Act: 5.0026. Min Act: -0.1700
Data Index: 389408 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9713. Min Act: -0.1700
Data Index: 3005242 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9713. Min Act: -0.1700
Data Index: 6970415 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9713. Min Act: -0.1700
Data Index: 8109373 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9713. Min Act: -0.1700
Data Index: 7239108 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9401. Min Act: -0.1700
Data Index: 8186417 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9401. Min Act: -0.1700
Data Index: 7267513 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9401. Min Act: -0.1700
Data Index: 1996349 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9088. Min Act: -0.1700
Data Index: 2873640 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9401. Min Act: -0.1700
Data Index: 1765632 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9401. Min Act: -0.1700
Data Index: 28535 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2213. Min Range: -5.2213
Max Act: 4.9401. Min Act: -0.1700
Data Index: 28522 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19