Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.4185. Min Act: -0.1700
Data Index: 7376821 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.3560. Min Act: -0.1700
Data Index: 421637 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2935. Min Act: -0.1700
Data Index: 7506890 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.3248. Min Act: -0.1700
Data Index: 5517923 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2623. Min Act: -0.1700
Data Index: 1722251 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2623. Min Act: -0.1700
Data Index: 1649114 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2310. Min Act: -0.1700
Data Index: 3272677 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2623. Min Act: -0.1700
Data Index: 2837852 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2623. Min Act: -0.1700
Data Index: 7799109 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2623. Min Act: -0.1700
Data Index: 1220173 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.1998. Min Act: -0.1700
Data Index: 2699143 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2310. Min Act: -0.1700
Data Index: 7544379 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2310. Min Act: -0.1700
Data Index: 8101297 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2310. Min Act: -0.1700
Data Index: 6170687 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2310. Min Act: -0.1700
Data Index: 2242773 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2623. Min Act: -0.1700
Data Index: 2688336 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2310. Min Act: -0.1700
Data Index: 3659113 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.1998. Min Act: -0.1700
Data Index: 5575034 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.1998. Min Act: -0.1700
Data Index: 5595765 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4185. Min Range: -5.4185
Max Act: 5.2310. Min Act: -0.1700
Data Index: 5651235 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19