Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.5822. Min Act: -0.1700
Data Index: 3134377 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.3947. Min Act: -0.1700
Data Index: 3134376 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.4259. Min Act: -0.1700
Data Index: 3134370 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.3322. Min Act: -0.1700
Data Index: 3134392 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.3009. Min Act: -0.1700
Data Index: 3134367 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.2384. Min Act: -0.1700
Data Index: 3134396 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.1759. Min Act: -0.1700
Data Index: 8233675 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.1134. Min Act: -0.1700
Data Index: 4382317 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.1134. Min Act: -0.1700
Data Index: 7716206 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.0509. Min Act: -0.1700
Data Index: 6177824 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.0509. Min Act: -0.1700
Data Index: 7220886 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.0197. Min Act: -0.1700
Data Index: 3038717 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5822. Min Range: -5.5822
Max Act: 4.8947. Min Act: -0.1700
Data Index: 2767363 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5822. Min Range: -5.5822
Max Act: 5.0197. Min Act: -0.1700
Data Index: 4419306 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5822. Min Range: -5.5822
Max Act: 4.9884. Min Act: -0.1700
Data Index: 7540039 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5822. Min Range: -5.5822
Max Act: 4.9884. Min Act: -0.1700
Data Index: 2669959 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5822. Min Range: -5.5822
Max Act: 4.9572. Min Act: -0.1699
Data Index: 5027290 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5822. Min Range: -5.5822
Max Act: 4.9884. Min Act: -0.1700
Data Index: 8575611 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5822. Min Range: -5.5822
Max Act: 4.9572. Min Act: -0.1700
Data Index: 1958784 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5822. Min Range: -5.5822
Max Act: 4.9259. Min Act: -0.1700
Data Index: 5534612 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19