Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 125 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.5580. Min Act: -0.1700
Data Index: 6814611 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.5268. Min Act: -0.1700
Data Index: 4506624 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.4643. Min Act: -0.1700
Data Index: 6100035 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.4643. Min Act: -0.1700
Data Index: 7696442 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.4330. Min Act: -0.1700
Data Index: 5899526 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.4018. Min Act: -0.1700
Data Index: 7833129 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.4018. Min Act: -0.1700
Data Index: 8447411 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.4018. Min Act: -0.1700
Data Index: 7224886 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.4018. Min Act: -0.1700
Data Index: 2055682 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.4018. Min Act: -0.1700
Data Index: 2572091 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3705. Min Act: -0.1700
Data Index: 7833044 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3393. Min Act: -0.1700
Data Index: 5549397 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3393. Min Act: -0.1700
Data Index: 8265235 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3393. Min Act: -0.1700
Data Index: 7115780 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3393. Min Act: -0.1700
Data Index: 5498642 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3393. Min Act: -0.1700
Data Index: 4398254 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3393. Min Act: -0.1700
Data Index: 7935745 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3393. Min Act: -0.1700
Data Index: 2835070 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3393. Min Act: -0.1700
Data Index: 319062 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5580. Min Range: -5.5580
Max Act: 5.3393. Min Act: -0.1700
Data Index: 3664632 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19