Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2082 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2120. Min Range: -6.2120
Max Act: 6.2120. Min Act: -0.1700
Data Index: 6297268 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2120. Min Range: -6.2120
Max Act: 6.1808. Min Act: -0.1700
Data Index: 7361155 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2120. Min Range: -6.2120
Max Act: 6.1808. Min Act: -0.1700
Data Index: 5242563 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2120. Min Range: -6.2120
Max Act: 6.0558. Min Act: -0.1700
Data Index: 3561829 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2120. Min Range: -6.2120
Max Act: 6.0558. Min Act: -0.1700
Data Index: 2897916 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.9933. Min Act: -0.1700
Data Index: 5108626 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.9933. Min Act: -0.1700
Data Index: 4417725 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.8995. Min Act: -0.1700
Data Index: 6950725 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.9308. Min Act: -0.1700
Data Index: 969570 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.8995. Min Act: -0.1700
Data Index: 281928 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.8370. Min Act: -0.1700
Data Index: 4935514 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.8683. Min Act: -0.1700
Data Index: 4653058 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.7745. Min Act: -0.1700
Data Index: 6173081 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.7745. Min Act: -0.1700
Data Index: 5400787 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.7433. Min Act: -0.1700
Data Index: 6877623 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.7433. Min Act: -0.1700
Data Index: 6740356 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.7120. Min Act: -0.1700
Data Index: 5883138 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.6808. Min Act: -0.1700
Data Index: 3721151 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.6808. Min Act: -0.1700
Data Index: 4261510 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2120. Min Range: -6.2120
Max Act: 5.6808. Min Act: -0.1700
Data Index: 7844945 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19