Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1105. Min Range: -8.1105
Max Act: 8.1105. Min Act: -0.1700
Data Index: 5113261 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1105. Min Range: -8.1105
Max Act: 8.0480. Min Act: -0.1700
Data Index: 5617880 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.9855. Min Act: -0.1700
Data Index: 6823268 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.9230. Min Act: -0.1700
Data Index: 5189411 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.9230. Min Act: -0.1700
Data Index: 2265595 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.9855. Min Act: -0.1700
Data Index: 6955636 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.9230. Min Act: -0.1700
Data Index: 8786514 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.8917. Min Act: -0.1700
Data Index: 260698 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.9230. Min Act: -0.1700
Data Index: 96449 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.8605. Min Act: -0.1700
Data Index: 3686538 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.7980. Min Act: -0.1700
Data Index: 8411521 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.8292. Min Act: -0.1700
Data Index: 2762779 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.8292. Min Act: -0.1700
Data Index: 4315332 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.7667. Min Act: -0.1700
Data Index: 3818345 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.7667. Min Act: -0.1700
Data Index: 6357897 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.7355. Min Act: -0.1700
Data Index: 1849042 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.7355. Min Act: -0.1700
Data Index: 6566270 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.7355. Min Act: -0.1700
Data Index: 4446674 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.7042. Min Act: -0.1700
Data Index: 2249904 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1105. Min Range: -8.1105
Max Act: 7.7355. Min Act: -0.1700
Data Index: 499511 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19