Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2483 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.6845. Min Act: -0.1700
Data Index: 7125675 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.6220. Min Act: -0.1700
Data Index: 8266181 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.6220. Min Act: -0.1700
Data Index: 7124036 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.5595. Min Act: -0.1700
Data Index: 8409408 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.5595. Min Act: -0.1700
Data Index: 6480954 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4970. Min Act: -0.1700
Data Index: 8346333 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.5907. Min Act: -0.1700
Data Index: 6052864 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.5595. Min Act: -0.1700
Data Index: 7902622 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.5282. Min Act: -0.1700
Data Index: 2480590 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4970. Min Act: -0.1700
Data Index: 2291093 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4970. Min Act: -0.1700
Data Index: 8814020 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4345. Min Act: -0.1700
Data Index: 7448580 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4657. Min Act: -0.1700
Data Index: 5101135 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4657. Min Act: -0.1700
Data Index: 2479360 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4657. Min Act: -0.1700
Data Index: 16039 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4657. Min Act: -0.1700
Data Index: 7231362 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4970. Min Act: -0.1700
Data Index: 680151 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4345. Min Act: -0.1700
Data Index: 4445760 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4657. Min Act: -0.1700
Data Index: 6441448 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6845. Min Range: -4.6845
Max Act: 4.4345. Min Act: -0.1700
Data Index: 2868481 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19