Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.3547. Min Act: -0.1700
Data Index: 961080 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2922. Min Act: -0.1700
Data Index: 7499964 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 1210982 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 758817 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 5372897 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 5935366 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1985. Min Act: -0.1700
Data Index: 3398236 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1672. Min Act: -0.1700
Data Index: 5276958 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1047. Min Act: -0.1700
Data Index: 5946401 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0735. Min Act: -0.1700
Data Index: 1210981 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0735. Min Act: -0.1700
Data Index: 5317318 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0735. Min Act: -0.1700
Data Index: 2665025 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0735. Min Act: -0.1700
Data Index: 5602453 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0422. Min Act: -0.1700
Data Index: 3158315 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0422. Min Act: -0.1700
Data Index: 5935367 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0422. Min Act: -0.1700
Data Index: 3490864 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0422. Min Act: -0.1700
Data Index: 7436 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0110. Min Act: -0.1700
Data Index: 987953 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0110. Min Act: -0.1700
Data Index: 3899233 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.0110. Min Act: -0.1700
Data Index: 2224694 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19