Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.6881. Min Act: -0.1700
Data Index: 3288964 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.6568. Min Act: -0.1700
Data Index: 6383966 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.6568. Min Act: -0.1700
Data Index: 5589301 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.5316. Min Act: -0.1700
Data Index: 6629756 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.5316. Min Act: -0.1700
Data Index: 2509701 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.5316. Min Act: -0.1700
Data Index: 730997 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.5002. Min Act: -0.1700
Data Index: 5620118 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.5002. Min Act: -0.1700
Data Index: 4165278 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.5002. Min Act: -0.1700
Data Index: 8118885 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4376. Min Act: -0.1700
Data Index: 8820495 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4689. Min Act: -0.1700
Data Index: 3299948 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4689. Min Act: -0.1700
Data Index: 395220 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4689. Min Act: -0.1700
Data Index: 6019737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4689. Min Act: -0.1700
Data Index: 2475101 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4689. Min Act: -0.1700
Data Index: 8782085 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4689. Min Act: -0.1700
Data Index: 4980793 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4376. Min Act: -0.1700
Data Index: 35478 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4376. Min Act: -0.1700
Data Index: 5318404 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4376. Min Act: -0.1700
Data Index: 5713298 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6881. Min Range: -3.6881
Max Act: 3.4376. Min Act: -0.1700
Data Index: 6111096 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19