Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3172. Min Range: -6.3172
Max Act: 6.3172. Min Act: -0.1700
Data Index: 4027622 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3172. Min Range: -6.3172
Max Act: 6.1610. Min Act: -0.1700
Data Index: 5854603 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3172. Min Range: -6.3172
Max Act: 6.0360. Min Act: -0.1700
Data Index: 2706908 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3172. Min Range: -6.3172
Max Act: 6.0360. Min Act: -0.1700
Data Index: 4427938 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3172. Min Range: -6.3172
Max Act: 6.0047. Min Act: -0.1700
Data Index: 2135713 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.9422. Min Act: -0.1700
Data Index: 1146826 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.9735. Min Act: -0.1700
Data Index: 2526863 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.9422. Min Act: -0.1700
Data Index: 4795651 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.9422. Min Act: -0.1700
Data Index: 7919517 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.9110. Min Act: -0.1700
Data Index: 4178415 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.8797. Min Act: -0.1700
Data Index: 7242735 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.8485. Min Act: -0.1700
Data Index: 45859 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.8797. Min Act: -0.1700
Data Index: 977017 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.8485. Min Act: -0.1700
Data Index: 6840659 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.8485. Min Act: -0.1700
Data Index: 503817 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.8172. Min Act: -0.1700
Data Index: 5787407 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.8172. Min Act: -0.1700
Data Index: 2517390 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.7860. Min Act: -0.1700
Data Index: 3848090 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.7860. Min Act: -0.1700
Data Index: 4909932 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3172. Min Range: -6.3172
Max Act: 5.7547. Min Act: -0.1700
Data Index: 4611938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19