Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4303 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.4964. Min Act: -0.1700
Data Index: 2094677 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.3554. Min Act: -0.1700
Data Index: 1940570 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.3554. Min Act: -0.1700
Data Index: 1111245 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.3397. Min Act: -0.1700
Data Index: 2579886 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.3240. Min Act: -0.1700
Data Index: 4302672 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.3240. Min Act: -0.1700
Data Index: 6420528 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.3240. Min Act: -0.1700
Data Index: 7433238 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.3083. Min Act: -0.1700
Data Index: 6852870 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2926. Min Act: -0.1700
Data Index: 5440290 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2769. Min Act: -0.1700
Data Index: 4738577 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2769. Min Act: -0.1700
Data Index: 326305 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2455. Min Act: -0.1700
Data Index: 273091 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2769. Min Act: -0.1700
Data Index: 7746288 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2455. Min Act: -0.1700
Data Index: 4058336 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2455. Min Act: -0.1700
Data Index: 2760443 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2298. Min Act: -0.1700
Data Index: 6780009 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2298. Min Act: -0.1700
Data Index: 7835991 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2298. Min Act: -0.1700
Data Index: 8778 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2298. Min Act: -0.1700
Data Index: 748298 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4964. Min Range: -3.4964
Max Act: 3.2298. Min Act: -0.1700
Data Index: 4219656 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19