Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.3311. Min Act: -0.1700
Data Index: 2251676 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.2061. Min Act: -0.1700
Data Index: 2274969 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.2061. Min Act: -0.1700
Data Index: 4975429 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.1436. Min Act: -0.1700
Data Index: 1596072 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.1124. Min Act: -0.1700
Data Index: 6829487 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.1124. Min Act: -0.1700
Data Index: 663949 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.0811. Min Act: -0.1700
Data Index: 5834633 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.0186. Min Act: -0.1700
Data Index: 1966442 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.0499. Min Act: -0.1700
Data Index: 2884930 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.9874. Min Act: -0.1700
Data Index: 5186777 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3311. Min Range: -6.3311
Max Act: 6.0186. Min Act: -0.1700
Data Index: 4951897 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.9874. Min Act: -0.1700
Data Index: 6500792 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.9874. Min Act: -0.1700
Data Index: 28257 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.9874. Min Act: -0.1700
Data Index: 941519 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.9249. Min Act: -0.1700
Data Index: 2828091 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.9249. Min Act: -0.1700
Data Index: 2785621 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.9249. Min Act: -0.1700
Data Index: 135117 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.9249. Min Act: -0.1700
Data Index: 1791518 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.8624. Min Act: -0.1700
Data Index: 1178616 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3311. Min Range: -6.3311
Max Act: 5.8311. Min Act: -0.1700
Data Index: 3923819 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19