Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9693. Min Act: -0.1700
Data Index: 6341067 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.5943. Min Act: -0.1700
Data Index: 8497786 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.5005. Min Act: -0.1700
Data Index: 4441571 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.5005. Min Act: -0.1700
Data Index: 3604152 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.4693. Min Act: -0.1700
Data Index: 7147079 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.4380. Min Act: -0.1700
Data Index: 5828780 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3755. Min Act: -0.1700
Data Index: 2915521 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3755. Min Act: -0.1700
Data Index: 3917581 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3755. Min Act: -0.1700
Data Index: 2345405 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3443. Min Act: -0.1700
Data Index: 1426510 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3130. Min Act: -0.1700
Data Index: 7889570 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3130. Min Act: -0.1700
Data Index: 2834625 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3130. Min Act: -0.1700
Data Index: 1481277 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3130. Min Act: -0.1700
Data Index: 1174025 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.3130. Min Act: -0.1700
Data Index: 6305657 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2818. Min Act: -0.1700
Data Index: 1851971 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2818. Min Act: -0.1700
Data Index: 2689962 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2818. Min Act: -0.1700
Data Index: 3751894 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2818. Min Act: -0.1700
Data Index: 6725618 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.2818. Min Act: -0.1700
Data Index: 137824 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19