Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6291 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.4043. Min Act: -0.1700
Data Index: 2166895 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.3418. Min Act: -0.1700
Data Index: 2404572 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.3418. Min Act: -0.1700
Data Index: 2535800 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.3105. Min Act: -0.1700
Data Index: 3815106 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.3105. Min Act: -0.1700
Data Index: 5113587 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.3105. Min Act: -0.1700
Data Index: 299871 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.3105. Min Act: -0.1700
Data Index: 487784 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.3105. Min Act: -0.1700
Data Index: 1183031 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.2480. Min Act: -0.1700
Data Index: 613819 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.2480. Min Act: -0.1700
Data Index: 5383354 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.1855. Min Act: -0.1700
Data Index: 6019887 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.2168. Min Act: -0.1700
Data Index: 739189 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.1855. Min Act: -0.1700
Data Index: 4015237 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.1230. Min Act: -0.1700
Data Index: 4747742 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.1543. Min Act: -0.1700
Data Index: 3865353 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.1543. Min Act: -0.1700
Data Index: 3497729 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.1855. Min Act: -0.1700
Data Index: 5843203 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.1230. Min Act: -0.1700
Data Index: 5581445 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.1230. Min Act: -0.1700
Data Index: 4586304 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4043. Min Range: -4.4043
Max Act: 4.1230. Min Act: -0.1700
Data Index: 5815646 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19