Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2726. Min Range: -7.2726
Max Act: 7.2726. Min Act: -0.1700
Data Index: 8220091 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2726. Min Range: -7.2726
Max Act: 7.0226. Min Act: -0.1700
Data Index: 3892404 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.8976. Min Act: -0.1700
Data Index: 2925525 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.8663. Min Act: -0.1700
Data Index: 7398026 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.8351. Min Act: -0.1700
Data Index: 5726549 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.6163. Min Act: -0.1700
Data Index: 6092569 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.6163. Min Act: -0.1700
Data Index: 1741876 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.5851. Min Act: -0.1700
Data Index: 7044161 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.5538. Min Act: -0.1700
Data Index: 4946028 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.6163. Min Act: -0.1700
Data Index: 6591773 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.5226. Min Act: -0.1700
Data Index: 2234664 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.4601. Min Act: -0.1700
Data Index: 4276221 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.4601. Min Act: -0.1700
Data Index: 5219052 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.4601. Min Act: -0.1700
Data Index: 2278745 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.4288. Min Act: -0.1700
Data Index: 8699385 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.4601. Min Act: -0.1700
Data Index: 3312526 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.4913. Min Act: -0.1700
Data Index: 5981675 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.4288. Min Act: -0.1700
Data Index: 2247126 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.4288. Min Act: -0.1700
Data Index: 3960562 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2726. Min Range: -7.2726
Max Act: 6.4288. Min Act: -0.1700
Data Index: 8282607 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19