Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4417 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.4244. Min Act: -0.1700
Data Index: 6120111 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.4244. Min Act: -0.1700
Data Index: 5980806 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.2994. Min Act: -0.1700
Data Index: 8268984 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.3306. Min Act: -0.1700
Data Index: 7423527 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.2994. Min Act: -0.1700
Data Index: 4289549 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.2681. Min Act: -0.1700
Data Index: 2277957 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.2681. Min Act: -0.1700
Data Index: 6682273 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.2369. Min Act: -0.1700
Data Index: 6775034 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.2056. Min Act: -0.1700
Data Index: 121941 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.1744. Min Act: -0.1700
Data Index: 1636393 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.1744. Min Act: -0.1700
Data Index: 2327499 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.1431. Min Act: -0.1700
Data Index: 4924088 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.1431. Min Act: -0.1700
Data Index: 4042555 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.1119. Min Act: -0.1700
Data Index: 8710186 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.1119. Min Act: -0.1700
Data Index: 2447775 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.0181. Min Act: -0.1700
Data Index: 943899 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.0494. Min Act: -0.1700
Data Index: 1588710 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.0494. Min Act: -0.1700
Data Index: 7213495 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.0494. Min Act: -0.1700
Data Index: 6682270 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4244. Min Range: -6.4244
Max Act: 6.0494. Min Act: -0.1700
Data Index: 8092598 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19