Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.4384. Min Act: -0.1699
Data Index: 916314 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.2196. Min Act: -0.1700
Data Index: 5590102 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.1884. Min Act: -0.1700
Data Index: 8652837 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.1884. Min Act: -0.1697
Data Index: 5342841 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.1571. Min Act: -0.1700
Data Index: 6987009 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.1571. Min Act: -0.1700
Data Index: 6536440 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.1571. Min Act: -0.1700
Data Index: 264349 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.1259. Min Act: -0.1700
Data Index: 6874050 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.1259. Min Act: -0.1700
Data Index: 2874567 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.1571. Min Act: -0.1700
Data Index: 5770649 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.0946. Min Act: -0.1700
Data Index: 2622091 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.1259. Min Act: -0.1700
Data Index: 5590084 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.0946. Min Act: -0.1700
Data Index: 1448265 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.0946. Min Act: -0.1700
Data Index: 4218576 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.0634. Min Act: -0.1699
Data Index: 322211 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.0634. Min Act: -0.1700
Data Index: 4174467 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.0634. Min Act: -0.1700
Data Index: 2119017 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.0634. Min Act: -0.1700
Data Index: 677398 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.0634. Min Act: -0.1700
Data Index: 22654 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4384. Min Range: -5.4384
Max Act: 5.0634. Min Act: -0.1695
Data Index: 5172257 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19