Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5499 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.4254. Min Act: -0.1700
Data Index: 1732399 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.4567. Min Act: -0.1700
Data Index: 7207017 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.3629. Min Act: -0.1700
Data Index: 890922 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.3316. Min Act: -0.1700
Data Index: 1174201 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.3004. Min Act: -0.1700
Data Index: 1635216 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.3004. Min Act: -0.1700
Data Index: 7827745 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.3004. Min Act: -0.1700
Data Index: 4479755 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2691. Min Act: -0.1700
Data Index: 5122347 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.3004. Min Act: -0.1700
Data Index: 2182604 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2691. Min Act: -0.1700
Data Index: 4100335 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2691. Min Act: -0.1700
Data Index: 6152228 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2691. Min Act: -0.1700
Data Index: 1010306 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2379. Min Act: -0.1700
Data Index: 5976523 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2379. Min Act: -0.1700
Data Index: 1373875 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2379. Min Act: -0.1700
Data Index: 7455036 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2066. Min Act: -0.1700
Data Index: 7101132 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2066. Min Act: -0.1700
Data Index: 7204520 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2066. Min Act: -0.1700
Data Index: 228983 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2066. Min Act: -0.1700
Data Index: 1106422 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4567. Min Range: -4.4567
Max Act: 4.2066. Min Act: -0.1700
Data Index: 4901996 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19