Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.5964. Min Act: -0.1700
Data Index: 7487345 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.5652. Min Act: -0.1700
Data Index: 33407 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.5339. Min Act: -0.1700
Data Index: 8418376 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.5027. Min Act: -0.1700
Data Index: 8067956 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.5027. Min Act: -0.1700
Data Index: 3826144 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.5027. Min Act: -0.1700
Data Index: 1584183 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.5339. Min Act: -0.1700
Data Index: 1353551 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.4714. Min Act: -0.1700
Data Index: 2486237 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.4714. Min Act: -0.1700
Data Index: 5351062 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.4402. Min Act: -0.1700
Data Index: 4067734 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.4089. Min Act: -0.1700
Data Index: 8191007 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.4089. Min Act: -0.1700
Data Index: 927189 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.4402. Min Act: -0.1700
Data Index: 8271844 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.4089. Min Act: -0.1700
Data Index: 4215656 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.4089. Min Act: -0.1700
Data Index: 6863255 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.3777. Min Act: -0.1700
Data Index: 8120194 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.3777. Min Act: -0.1700
Data Index: 5653083 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.3777. Min Act: -0.1700
Data Index: 2587820 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.3777. Min Act: -0.1700
Data Index: 4344077 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5964. Min Range: -5.5964
Max Act: 5.3777. Min Act: -0.1700
Data Index: 880287 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19