Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.4054. Min Act: -0.1700
Data Index: 4086302 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.3429. Min Act: -0.1700
Data Index: 698172 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.1242. Min Act: -0.1700
Data Index: 142763 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.1554. Min Act: -0.1700
Data Index: 7439778 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.0929. Min Act: -0.1700
Data Index: 7745117 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.0929. Min Act: -0.1700
Data Index: 5288554 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.0929. Min Act: -0.1700
Data Index: 3120451 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.0929. Min Act: -0.1700
Data Index: 460059 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.0617. Min Act: -0.1700
Data Index: 8705546 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.0304. Min Act: -0.1700
Data Index: 1615671 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4054. Min Range: -7.4054
Max Act: 7.0304. Min Act: -0.1699
Data Index: 8803693 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4054. Min Range: -7.4054
Max Act: 6.9992. Min Act: -0.1700
Data Index: 8522851 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4054. Min Range: -7.4054
Max Act: 6.9679. Min Act: -0.1700
Data Index: 61799 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4054. Min Range: -7.4054
Max Act: 6.9367. Min Act: -0.1700
Data Index: 5039124 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4054. Min Range: -7.4054
Max Act: 6.9054. Min Act: -0.1700
Data Index: 6057089 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4054. Min Range: -7.4054
Max Act: 6.9367. Min Act: -0.1700
Data Index: 7828799 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4054. Min Range: -7.4054
Max Act: 6.9367. Min Act: -0.1700
Data Index: 8824774 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4054. Min Range: -7.4054
Max Act: 6.9367. Min Act: -0.1700
Data Index: 4139531 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4054. Min Range: -7.4054
Max Act: 6.9367. Min Act: -0.1700
Data Index: 8482734 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4054. Min Range: -7.4054
Max Act: 6.9054. Min Act: -0.1700
Data Index: 7077184 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19